# Research Papers — 2025-11 · bundle page 98 of 197 > Full-text markdown of papers #4851–4900 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-11/page/98 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/97.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/99.md) ### Think, Speak, Decide: Language-Augmented Multi-Agent Reinforcement Learning for Economic Decision-Making Authors: Heyang Ma, Qirui Mi, Qipeng Yang, Zijun Fan, Bo Li, Haifeng Zhang Published: 2025-11-17 Categories: cs.AI, econ.GN arXiv: https://arxiv.org/abs/2511.12876v4 Economic decision-making depends not only on structured signals such as prices and taxes, but also on unstructured language, including peer dialogue and media narratives. While multi-agent reinforcement learning (MARL) has shown promise in optimizing economic decisions, it struggles with the semantic ambiguity and contextual richness of language. We propose LAMP (Language-Augmented Multi-Agent Policy), a framework that integrates language into economic decision-making and narrows the gap to real-world settings. LAMP follows a Think-Speak-Decide pipeline: (1) Think interprets numerical observations to extract short-term shocks and long-term trends, caching high-value reasoning trajectories; (2) Speak crafts and exchanges strategic messages based on reasoning, updating beliefs by parsing peer communications; and (3) Decide fuses numerical data, reasoning, and reflections into a MARL policy to optimize language-augmented decision-making. Experiments in economic simulation show that LAMP outperforms both MARL and LLM-only baselines in cumulative return (+63.5%, +34.0%), robustness (+18.8%, +59.4%), and interpretability. These results demonstrate the potential of language-augmented policies to deliver more effective and robust economic strategies. --- ### Classification of Hope in Textual Data using Transformer-Based Models Authors: Chukwuebuka Fortunate Ijezue, Tania-Amanda Fredrick Eneye, Maaz Amjad Published: 2025-11-17 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.12874v1 This paper presents a transformer-based approach for classifying hope expressions in text. We developed and compared three architectures (BERT, GPT-2, and DeBERTa) for both binary classification (Hope vs. Not Hope) and multiclass categorization (five hope-related categories). Our initial BERT implementation achieved 83.65% binary and 74.87% multiclass accuracy. In the extended comparison, BERT demonstrated superior performance (84.49% binary, 72.03% multiclass accuracy) while requiring significantly fewer computational resources (443s vs. 704s training time) than newer architectures. GPT-2 showed lowest overall accuracy (79.34% binary, 71.29% multiclass), while DeBERTa achieved moderate results (80.70% binary, 71.56% multiclass) but at substantially higher computational cost (947s for multiclass training). Error analysis revealed architecture-specific strengths in detecting nuanced hope expressions, with GPT-2 excelling at sarcasm detection (92.46% recall). This study provides a framework for computational analysis of hope, with applications in mental health and social media analysis, while demonstrating that architectural suitability may outweigh model size for specialized emotion detection tasks. --- ### View-aware Cross-modal Distillation for Multi-view Action Recognition Authors: Trung Thanh Nguyen, Yasutomo Kawanishi, Vijay John, Takahiro Komamizu, Ichiro Ide Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12870v2 The widespread use of multi-sensor systems has increased research in multi-view action recognition. While existing approaches in multi-view setups with fully overlapping sensors benefit from consistent view coverage, partially overlapping settings where actions are visible in only a subset of views remain underexplored. This challenge becomes more severe in real-world scenarios, as many systems provide only limited input modalities and rely on sequence-level annotations instead of dense frame-level labels. In this study, we propose View-aware Cross-modal Knowledge Distillation (ViCoKD), a framework that distills knowledge from a fully supervised multi-modal teacher to a modality- and annotation-limited student. ViCoKD employs a cross-modal adapter with cross-modal attention, allowing the student to exploit multi-modal correlations while operating with incomplete modalities. Moreover, we propose a View-aware Consistency module to address view misalignment, where the same action may appear differently or only partially across viewpoints. It enforces prediction alignment when the action is co-visible across views, guided by human-detection masks and confidence-weighted Jensen-Shannon divergence between their predicted class distributions. Experiments on the real-world MultiSensor-Home dataset show that ViCoKD consistently outperforms competitive distillation methods across multiple backbones and environments, delivering significant gains and surpassing the teacher model under limited conditions. --- ### On the Fundamental Limits of LLMs at Scale Authors: Muhammad Ahmed Mohsin, Muhammad Umer, Ahsan Bilal, Zeeshan Memon, Muhammad Ibtsaam Qadir, Sagnik Bhattacharya, Hassan Rizwan, Abhiram R. Gorle, Maahe Zehra Kazmi, Nukhba Amir, Ali Subhan, Muhammad Usman Rafique et al. Published: 2025-11-17 Categories: cs.LG, cs.AI, cs.DC, cs.IT, cs.MA arXiv: https://arxiv.org/abs/2511.12869v2 Large Language Models (LLMs) have benefited enormously from scaling, yet these gains are bounded by five fundamental limitations: (1) hallucination, (2) context compression, (3) reasoning degradation, (4) retrieval fragility, and (5) multimodal misalignment. While existing surveys describe these phenomena empirically, they lack a rigorous theoretical synthesis connecting them to the foundational limits of computation, information, and learning. This work closes that gap by presenting a unified, proof-informed framework that formalizes the innate theoretical ceilings of LLM scaling. First, computability and uncomputability imply an irreducible residue of error: for any computably enumerable model family, diagonalization guarantees inputs on which some model must fail, and undecidable queries (e.g., halting-style tasks) induce infinite failure sets for all computable predictors. Second, information-theoretic and statistical constraints bound attainable accuracy even on decidable tasks, finite description length enforces compression error, and long-tail factual knowledge requires prohibitive sample complexity. Third, geometric and computational effects compress long contexts far below their nominal size due to positional under-training, encoding attenuation, and softmax crowding. We further show how likelihood-based training favors pattern completion over inference, how retrieval under token limits suffers from semantic drift and coupling noise, and how multimodal scaling inherits shallow cross-modal alignment. Across sections, we pair theorems and empirical evidence to outline where scaling helps, where it saturates, and where it cannot progress, providing both theoretical foundations and practical mitigation paths like bounded-oracle retrieval, positional curricula, and sparse or hierarchical attention. --- ### Video Finetuning Improves Reasoning Between Frames Authors: Ruiqi Yang, Tian Yun, Zihan Wang, Ellie Pavlick Published: 2025-11-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.12868v1 Multimodal large language models (LLMs) have made rapid progress in visual understanding, yet their extension from images to videos often reduces to a naive concatenation of frame tokens. In this work, we investigate what video finetuning brings to multimodal LLMs. We propose Visual Chain-of-Thought (vCoT), an explicit reasoning process that generates transitional event descriptions between consecutive frames. Using vCoT, we systematically compare image-only LVLMs with their video-finetuned counterparts, both with and without access to these transitional cues. Our experiments show that vCoT significantly improves the performance of image-only models on long-form video question answering, while yielding only marginal gains for video-finetuned models. This suggests that the latter already capture frame-to-frame transitions implicitly. Moreover, we find that video models transfer this temporal reasoning ability to purely static settings, outperforming image models' baselines on relational visual reasoning tasks. --- ### Bootstrapping LLMs via Preference-Based Policy Optimization Authors: Chen Jia Published: 2025-11-17 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.12867v2 Bootstrapping large language models (LLMs) through preference-based policy optimization offers a promising direction for aligning model behavior with human preferences without relying on extensive manual annotations. In this work, we propose a novel preference-based policy optimization (PbPO) framework that formulates the learning process as a min-max game between the main policy and a reward model (RM). The RM is constrained within a confidence set derived from preference data to ensure reliable exploitation. Our iterative online algorithm actively collects preference data through guided exploration of the evolving policy, enabling continual self-improvement of both the policy and the RM. We provide theoretical guarantees for our method, establishing high-probability regret bounds for both settings with sequence-level RM and token-level RM, demonstrating its effectiveness in bootstrapping LLMs. Extensive experiments on five benchmarks show that our approach consistently outperforms existing state-of-the-art preference optimization techniques. --- ### An approach of deep reinforcement learning for maximizing the net present value of stochastic projects Authors: Wei Xu, Fan Yang, Qinyuan Cui, Zhi Chen Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.12865v1 This paper investigates a project with stochastic activity durations and cash flows under discrete scenarios, where activities must satisfy precedence constraints generating cash inflows and outflows. The objective is to maximize expected net present value (NPV) by accelerating inflows and deferring outflows. We formulate the problem as a discrete-time Markov Decision Process (MDP) and propose a Double Deep Q-Network (DDQN) approach. Comparative experiments demonstrate that DDQN outperforms traditional rigid and dynamic strategies, particularly in large-scale or highly uncertain environments, exhibiting superior computational capability, policy reliability, and adaptability. Ablation studies further reveal that the dual-network architecture mitigates overestimation of action values, while the target network substantially improves training convergence and robustness. These results indicate that DDQN not only achieves higher expected NPV in complex project optimization but also provides a reliable framework for stable and effective policy implementation. --- ### From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models Authors: Wenxin Zhu, Andong Chen, Yuchen Song, Kehai Chen, Conghui Zhu, Ziyan Chen, Tiejun Zhao Published: 2025-11-17 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2511.12861v4 With the remarkable success of Multimodal Large Language Models (MLLMs) in perception tasks, enhancing their complex reasoning capabilities has emerged as a critical research focus. Existing models still suffer from challenges such as opaque reasoning paths and insufficient generalization ability. Chain-of-Thought (CoT) reasoning, which has demonstrated significant efficacy in language models by enhancing reasoning transparency and output interpretability, holds promise for improving model reasoning capabilities when extended to the multimodal domain. This paper provides a systematic review centered on "Multimodal Chain-of-Thought" (MCoT). First, it analyzes the background and theoretical motivations for its inception from the perspectives of technical evolution and task demands. Then, it introduces mainstream MCoT methods from three aspects: CoT paradigms, the post-training stage, and the inference stage, while also analyzing their underlying mechanisms. Furthermore, the paper summarizes existing evaluation benchmarks and metrics, and discusses the application scenarios of MCoT. Finally, it analyzes the challenges currently facing MCoT and provides an outlook on its future research directions. --- ### BrainNormalizer: Anatomy-Informed Pseudo-Healthy Brain Reconstruction from Tumor MRI via Edge-Guided ControlNet Authors: Min Gu Kwak, Yeonju Lee, Hairong Wang, Kristin R. Swanson, Jing Li Published: 2025-11-17 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2511.12853v2 Brain tumors induce complex structural deformations that obscure the patient' s original neuroanatomy, making it difficult to distinguish tumor-induced changes from inherent anatomical variability. Reconstructing a subject-specific pseudo-healthy brain can provide a critical reference for such analysis, but this task is inherently counterfactual, as paired pre-tumor scans and explicit healthy guidance are unavailable. We propose BrainNormalizer, a diffusion-based framework for subject-specific pseudo-healthy brain MRI reconstruction that enables anatomy-informed reconstruction without requiring paired data or explicit healthy references. The framework learns anatomical priors and edge-based structural conditioning through a two-stage training strategy consisting of inpainting-based diffusion fine-tuning and ControlNet-based edge conditioning. At inference, counterfactual pseudo-healthy reconstruction is achieved through a deliberate misalignment strategy, where tumorous inputs are paired with non-tumorous prompts and mirrored contralateral edge maps. This allows subject-specific anatomical guidance to be constructed from the patient's own anatomy, enabling anatomically consistent pseudo-healthy reconstruction that preserves individual structural characteristics. Experiments on the BraTS2020 dataset demonstrate that BrainNormalizer achieves improved distributional realism, symmetry-based structural consistency, and reduced false positive detection compared to existing methods. These results indicate that the proposed framework provides a principled approach for subject-specific counterfactual reconstruction and supports downstream analysis of tumor-induced deformation. --- ### From Black-Box to White-Box: Control-Theoretic Neural Network Interpretability Authors: Jihoon Moon Published: 2025-11-17 Categories: cs.LG, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2511.12852v1 Deep neural networks achieve state of the art performance but remain difficult to interpret mechanistically. In this work, we propose a control theoretic framework that treats a trained neural network as a nonlinear state space system and uses local linearization, controllability and observability Gramians, and Hankel singular values to analyze its internal computation. For a given input, we linearize the network around the corresponding hidden activation pattern and construct a state space model whose state consists of hidden neuron activations. The input state and state output Jacobians define local controllability and observability Gramians, from which we compute Hankel singular values and associated modes. These quantities provide a principled notion of neuron and pathway importance: controllability measures how easily each neuron can be excited by input perturbations, observability measures how strongly each neuron influences the output, and Hankel singular values rank internal modes that carry input output energy. We illustrate the framework on simple feedforward networks, including a 1 2 2 1 SwiGLU network and a 2 3 3 2 GELU network. By comparing different operating points, we show how activation saturation reduces controllability, shrinks the dominant Hankel singular value, and shifts the dominant internal mode to a different subset of neurons. The proposed method turns a neural network into a collection of local white box dynamical models and suggests which internal directions are natural candidates for pruning or constraints to improve interpretability. --- ### NeuroLex: A Lightweight Domain Language Model for EEG Report Understanding and Generation Authors: Kang Yin, Hye-Bin Shin Published: 2025-11-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.12851v1 Clinical electroencephalogram (EEG) reports encode domain-specific linguistic conventions that general-purpose language models (LMs) fail to capture. We introduce NeuroLex, a lightweight domain-adaptive language model trained purely on EEG report text from the Harvard Electroencephalography Database. Unlike existing biomedical LMs, NeuroLex is tailored to the linguistic and diagnostic characteristics of EEG reporting, enabling it to serve as both an independent textual model and a decoder backbone for multimodal EEG-language systems. Using span-corruption pretraining and instruction-style fine-tuning on report polishing, paragraph summarization, and terminology question answering, NeuroLex learns the syntax and reasoning patterns characteristic of EEG interpretation. Comprehensive evaluations show that it achieves lower perplexity, higher extraction and summarization accuracy, better label efficiency, and improved robustness to negation and factual hallucination compared with general models of the same scale. With an EEG-aware linguistic backbone, NeuroLex bridges biomedical text modeling and brain-computer interface applications, offering a foundation for interpretable and language-driven neural decoding. --- ### Repeatability is not recovery: Quantifying algorithmic stability and topic recovery in Latent Dirichlet Allocation Authors: Saranzaya Magsarjav, Jonathan Tuke, Lewis Mitchell, Melissa Humphries Published: 2025-11-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.12850v2 Topic models are often judged by the consistency of their outputs across repeated runs, implicitly assuming that repeatable topic output is a successful recovery of the underlying topics. We show that this assumption is false: repeatability is not recovery. We introduce a stability framework that jointly measures consistency among repeated runs and accuracy relative to known ground truth. Because real-world corpora lack known topic structures, we generate synthetic corpora using the Latent Dirichlet Allocation (LDA) generative process, enabling direct evaluation of topic recovery. Across 50 repeated LDA runs on each corpus, we find that LDA reliably identifies the correct number of topics and frequently converges to highly consistent topic solutions. However, these repeatable solutions frequently fail to recover the true generating topics. Thus, internal stability should not be interpreted as evidence of correctness. Our results illustrate that stability and recovery are distinct properties of topic models and should be evaluated separately. Consequently, topic-model outputs should be validated using multiple complementary criteria before supporting substantive conclusions, particularly in high-stakes applications. --- ### Structured Imitation Learning of Interactive Policies through Inverse Games Authors: Max M. Sun, Todd Murphey Published: 2025-11-17 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2511.12848v1 Generative model-based imitation learning methods have recently achieved strong results in learning high-complexity motor skills from human demonstrations. However, imitation learning of interactive policies that coordinate with humans in shared spaces without explicit communication remains challenging, due to the significantly higher behavioral complexity in multi-agent interactions compared to non-interactive tasks. In this work, we introduce a structured imitation learning framework for interactive policies by combining generative single-agent policy learning with a flexible yet expressive game-theoretic structure. Our method explicitly separates learning into two steps: first, we learn individual behavioral patterns from multi-agent demonstrations using standard imitation learning; then, we structurally learn inter-agent dependencies by solving an inverse game problem. Preliminary results in a synthetic 5-agent social navigation task show that our method significantly improves non-interactive policies and performs comparably to the ground truth interactive policy using only 50 demonstrations. These results highlight the potential of structured imitation learning in interactive settings. --- ### RoS-Guard: Robust and Scalable Online Change Detection with Delay-Optimal Guarantees Authors: Zelin Zhu, Yancheng Huang, Kai Yang Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.12846v1 Online change detection (OCD) aims to rapidly identify change points in streaming data and is critical in applications such as power system monitoring, wireless network sensing, and financial anomaly detection. Existing OCD methods typically assume precise system knowledge, which is unrealistic due to estimation errors and environmental variations. Moreover, existing OCD methods often struggle with efficiency in large-scale systems. To overcome these challenges, we propose RoS-Guard, a robust and optimal OCD algorithm tailored for linear systems with uncertainty. Through a tight relaxation and reformulation of the OCD optimization problem, RoS-Guard employs neural unrolling to enable efficient parallel computation via GPU acceleration. The algorithm provides theoretical guarantees on performance, including expected false alarm rate and worst-case average detection delay. Extensive experiments validate the effectiveness of RoS-Guard and demonstrate significant computational speedup in large-scale system scenarios. --- ### Towards Reinforcement Learning from Neural Feedback: Mapping fNIRS Signals to Agent Performance Authors: Julia Santaniello, Matthew Russell, Benson Jiang, Donatello Sassaroli, Robert Jacob, Jivko Sinapov Published: 2025-11-17 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.12844v4 Reinforcement Learning from Human Feedback (RLHF) is a methodology that aligns agent behavior with human preferences by integrating user feedback into the agent's training process. This paper introduces a framework that guides agent training through implicit neural signals, with a focus on the neural classification problem. Our work presents and releases a novel dataset of functional near-infrared spectroscopy (fNIRS) recordings collected from 25 human participants across three domains: Pick-and-Place Robot, Lunar Lander, and Flappy Bird. We train multiple classifiers to predict varying levels of agent performance (optimal, suboptimal, or worst-case) from windows of preprocessed fNIRS features, achieving an average F1 score of 67% for binary and 46% for multi-class classification across conditions and domains. We also train multiple regressors to predict the degree of deviation between an agent's chosen action and a set of near-optimal policy actions, providing a continuous measure of performance. Finally, we evaluate cross-subject generalization and show that fine-tuning pre-trained models with a small sample of subject-specific data increases average F1 scores by 17% and 41% for binary and multi-class models, respectively. Our results demonstrate that mapping implicit fNIRS signals to agent performance is feasible and can be improved, laying the foundation for future Reinforcement Learning from Neural Feedback (RLNF) systems. --- ### Scalable learning of macroscopic stochastic dynamics Authors: Mengyi Chen, Pengru Huang, Kostya S. Novoselov, Qianxiao Li Published: 2025-11-17 Categories: physics.comp-ph, cs.LG arXiv: https://arxiv.org/abs/2511.12842v2 Macroscopic dynamical descriptions of complex physical systems are crucial for understanding and controlling material behavior. With the growing availability of data and compute, machine learning has become a promising alternative to first-principles methods to build accurate macroscopic models from microscopic trajectory simulations. However, for spatially extended systems, direct simulations of sufficiently large microscopic systems that inform macroscopic behavior is prohibitive. In this work, we propose a framework that learns the macroscopic dynamics of large stochastic microscopic systems using only small-system simulations. Our framework employs a partial evolution scheme to generate training data pairs by evolving large-system snapshots within local patches. We subsequently identify the closure variables associated with the macroscopic observables and learn the macroscopic dynamics using a custom loss. Furthermore, we introduce a hierarchical upsampling scheme that enables efficient generation of large-system snapshots from small-system trajectory distributions. We empirically demonstrate the accuracy and robustness of our framework through a variety of stochastic spatially extended systems, including those described by stochastic partial differential equations, idealised lattice spin systems, and a more realistic NbMoTa alloy system. --- ### Knowledge Graph Construction for Stock Markets with LLM-Based Explainable Reasoning Authors: Cheonsol Lee, Youngsang Jeong, Jeongyeol Shin, Huiju Kim, Jidong Kim Published: 2025-11-16 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2601.11528v1 The stock market is inherently complex, with interdependent relationships among companies, sectors, and financial indicators. Traditional research has largely focused on time-series forecasting and single-company analysis, relying on numerical data for stock price prediction. While such approaches can provide short-term insights, they are limited in capturing relational patterns, competitive dynamics, and explainable investment reasoning. To address these limitations, we propose a knowledge graph schema specifically designed for the stock market, modeling companies, sectors, stock indicators, financial statements, and inter-company relationships. By integrating this schema with large language models (LLMs), our approach enables multi-hop reasoning and relational queries, producing explainable and in-depth answers to complex financial questions. Figure1 illustrates the system pipeline, detailing the flow from data collection and graph construction to LLM-based query processing and answer generation. We validate the proposed framework through practical case studies on Korean listed companies, demonstrating its capability to extract insights that are difficult or impossible to obtain from traditional database queries alone. The results highlight the potential of combining knowledge graphs with LLMs for advanced investment analysis and decision support. --- ### SetupKit: Efficient Multi-Corner Setup/Hold Time Characterization Using Bias-Enhanced Interpolation and Active Learning Authors: Junzhuo Zhou, Ziwen Wang, Haoxuan Xia, Yuxin Yan, Chengyu Zhu, Ting-Jung Lin, Wei Xing, Lei He Published: 2025-11-16 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2512.00044v1 Accurate setup/hold time characterization is crucial for modern chip timing closure, but its reliance on potentially millions of SPICE simulations across diverse process-voltagetemperature (PVT) corners creates a major bottleneck, often lasting weeks or months. Existing methods suffer from slow search convergence and inefficient exploration, especially in the multi-corner setting. We introduce SetupKit, a novel framework designed to break this bottleneck using statistical intelligence, circuit analysis and active learning (AL). SetupKit integrates three key innovations: BEIRA, a bias-enhanced interpolation search derived from statistical error modeling to accelerate convergence by overcoming stagnation issues, initial search interval estimation by circuit analysis and AL strategy using Gaussian Process. This AL component intelligently learns PVT-timing correlations, actively guiding the expensive simulations to the most informative corners, thus minimizing redundancy in multicorner characterization. Evaluated on industrial 22nm standard cells across 16 PVT corners, SetupKit demonstrates a significant 2.4x overall CPU time reduction (from 720 to 290 days on a single core) compared to standard practices, drastically cutting characterization time. SetupKit offers a principled, learningbased approach to library characterization, addressing a critical EDA challenge and paving the way for more intelligent simulation management. --- ### On the Cross-lingual Transferability of Pre-trained wav2vec2-based Models Authors: Jonatas Grosman, Cassio Almeida, Guilherme Schardong, Hélio Lopes Published: 2025-11-16 Categories: cs.CL, cs.SD arXiv: https://arxiv.org/abs/2511.21704v1 Using representations provided by a large pre-trained model has become the primary strategy for achieving state-of-the-art results in a wide range of tasks. A recently proposed large pre-trained model, wav2vec 2.0, was seminal for several other works on pre-training large models on speech data. Many models are being pre-trained using the same architecture as wav2vec 2.0 and are getting state-of-the-art in various speech-related tasks. Previous work has demonstrated that the data used during the pre-training of these wav2vec2-based models can impact the model's performance in downstream tasks, and this should be taken into consideration before utilizing these models. However, few works have proposed investigating further how the transfer knowledge of these pre-trained models behaves in different languages, even when the target language differs from the one used during the model's pre-training. Our work aims to investigate the cross-lingual transferability of these wav2vec2-based models. We performed several fine-tuning experiments on the speech recognition task in 18 languages using 15 large pre-trained models. The results of our experiments showed us that the size of data used during the pre-training of these models is not as important to the final performance as the diversity. We noticed that the performance of Indo-European languages is superior to non-Indo-European languages in the evaluated models. We have observed a positive cross-lingual transfer of knowledge using monolingual models, which was evident in all the languages we used, but more pronounced when the language used during pre-training was more similar to the downstream task language. With these findings, we aim to assist the scientific community in utilizing existing wav2vec2-based pre-trained models, as well as facilitate the pre-training of new ones. --- ### Evaluating Embedding Generalization: How LLMs, LoRA, and SLERP Shape Representational Geometry Authors: Siyaxolisa Kabane Published: 2025-11-16 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.21703v1 We investigate the generalization properties of dense text embeddings when the embedding backbone is a large language model (LLM) versus when it is a non-LLM encoder, and we study the extent to which spherical linear interpolation (SLERP) model-merging mitigates over-specialization introduced by task-specific adaptation (e.g., LoRA). To make the comparison concrete and domain-agnostic, we design a controlled suite of experiments in which models embed short numerical sequences and are evaluated on their ability to cluster and classify those sequences according to well-defined number-theoretic properties. Our experimental protocol compares four families of models: (1) non-LLM encoders trained from scratch or fine-tuned for embeddings, (2) LLM-based encoders adapted with parameter-efficient methods (LoRA), (3) LLM-based encoders with LoRA followed by model souping merging into the base weights, and (4) the same LoRA-adapted LLMs merged using SLERP across checkpoints or stages. We evaluate representational quality with clustering indices (Silhouette and Davies Bouldin). We additionally analyze the use of kmeans labels to see if the embeddings encode any other information besides the one we are testing for. Empirically, we find that LLM-based backbones produce embeddings that better capture higher-order, compositional numeric patterns, but are prone to adapter dominance that degrades balanced generalization; SLERP merging consistently recovers base-model structure while retaining most task gains, yielding superior tradeoffs in clustering separability, and robustness compared to model souping or models that were not merged. --- ### CSV-Decode: Certifiable Sub-Vocabulary Decoding for Efficient Large Language Model Inference Authors: Dong Liu, Shu Wang, Yanxuan Yu, Haisheng Wang, Ben Lengerich Published: 2025-11-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.21702v2 Large language models face significant computational bottlenecks during inference due to the expensive output layer computation over large vocabularies. We present CSV-Decode, a novel approach that uses geometric upper bounds to construct small sub-vocabularies for each decoding step, enabling efficient sparse computation while maintaining dual correctness guarantees: exact top-$k$ certification and $\varepsilon$-certified softmax approximations. Our method clusters vocabulary embeddings offline and uses centroid-plus-radius bounds to identify which tokens can be safely omitted from computation. We provide a complete system implementation with sparse GEMV kernels, multi-GPU sharding, and CUDA Graph optimization. Experimental results demonstrate significant speedup over full vocabulary decoding while maintaining distributional guarantees and low fallback rates. Our code implementation available at \href{https://github.com/FastLM/CSV-Decode}{https://github.com/FastLM/CSV-Decode}. --- ### 47B Mixture-of-Experts Beats 671B Dense Models on Chinese Medical Examinations Authors: Chiung-Yi Tseng, Danyang Zhang, Tianyang Wang, Hongying Luo, Lu Chen, Junming Huang, Jibin Guan, Junfeng Hao, Junhao Song, Xinyuan Song, Ziqian Bi Published: 2025-11-16 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.21701v2 The rapid advancement of large language models(LLMs) has prompted significant interest in their potential applications in medical domains. This paper presents a comprehensive benchmark evaluation of 27 state-of-the-art LLMs on Chinese medical examination questions, encompassing seven medical specialties across two professional levels. We introduce a robust evaluation framework that assesses model performance on 2,800 carefully curated questions from cardiovascular, gastroenterology, hematology, infectious diseases, nephrology, neurology, and respiratory medicine domains. Our dataset distinguishes between attending physician and senior physician difficulty levels, providing nuanced insights into model capabilities across varying complexity. Our empirical analysis reveals substantial performance variations among models, with Mixtral-8x7B achieving the highest overall accuracy of 74.25%, followed by DeepSeek-R1-671B at 64.07%. Notably, we observe no consistent correlation between model size and performance, as evidenced by the strong performance of smaller mixture-of-experts architectures. The evaluation demonstrates significant performance gaps between medical specialties, with models generally performing better on cardiovascular and neurology questions compared to gastroenterology and nephrology domains. Furthermore, our analysis indicates minimal performance degradation between attending and senior physician levels for top-performing models, suggesting robust generalization capabilities. This benchmark provides critical insights for the deployment of LLMs in medical education and clinical decision support systems, highlighting both the promise and current limitations of these technologies in specialized medical contexts. --- ### JELV: A Judge of Edit-Level Validity for Evaluation and Automated Reference Expansion in Grammatical Error Correction Authors: Yuhao Zhan, Yuqing Zhang, Jing Yuan, Qixiang Ma, Zhiqi Yang, Yu Gu, Zemin Liu, Fei Wu Published: 2025-11-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.21700v2 Existing Grammatical Error Correction (GEC) systems suffer from limited reference diversity, leading to underestimated evaluation and restricted model generalization. To address this issue, we introduce the Judge of Edit-Level Validity (JELV), an automated framework to validate correction edits from grammaticality, faithfulness, and fluency. Using our proposed human-annotated Pair-wise Edit-level Validity Dataset (PEVData) as benchmark, JELV offers two implementations: a multi-turn LLM-as-Judges pipeline achieving 90% agreement with human annotators, and a distilled DeBERTa classifier with 85% precision on valid edits. We then apply JELV to reclassify misjudged false positives in evaluation and derive a comprehensive evaluation metric by integrating false positive decoupling and fluency scoring, resulting in state-of-the-art correlation with human judgments. We also apply JELV to filter LLM-generated correction candidates, expanding the BEA19's single-reference dataset containing 38,692 source sentences. Retraining top GEC systems on this expanded dataset yields measurable performance gains. JELV provides a scalable solution for enhancing reference diversity and strengthening both evaluation and model generalization. --- ### Cognitive bias in LLM reasoning compromises interpretation of clinical oncology notes Authors: Matthew W. Kenaston, Umair Ayub, Mihir Parmar, Muhammad Umair Anjum, Syed Arsalan Ahmed Naqvi, Priya Kumar, Samarth Rawal, Aadel A. Chaudhuri, Yousef Zakharia, Elizabeth I. Heath, Tanios S. Bekaii-Saab, Cui Tao et al. Published: 2025-11-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.20680v1 Despite high performance on clinical benchmarks, large language models may reach correct conclusions through faulty reasoning, a failure mode with safety implications for oncology decision support that is not captured by accuracy-based evaluation. In this two-cohort retrospective study, we developed a hierarchical taxonomy of reasoning errors from GPT-4 chain-of-thought responses to real oncology notes and tested its clinical relevance. Using breast and pancreatic cancer notes from the CORAL dataset, we annotated 600 reasoning traces to define a three-tier taxonomy mapping computational failures to cognitive bias frameworks. We validated the taxonomy on 822 responses from prostate cancer consult notes spanning localized through metastatic disease, simulating extraction, analysis, and clinical recommendation tasks. Reasoning errors occurred in 23 percent of interpretations and dominated overall errors, with confirmation bias and anchoring bias most common. Reasoning failures were associated with guideline-discordant and potentially harmful recommendations, particularly in advanced disease management. Automated evaluators using state-of-the-art language models detected error presence but could not reliably classify subtypes. These findings show that large language models may provide fluent but clinically unsafe recommendations when reasoning is flawed. The taxonomy provides a generalizable framework for evaluating and improving reasoning fidelity before clinical deployment. --- ### Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring Authors: Melika Ayoughi, Pascal Mettes, Paul Groth Published: 2025-11-16 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.20679v1 Hyperbolic geometry is an effective geometry for embedding hierarchical data structures. Hyperbolic learning has therefore become increasingly prominent in machine learning applications where data is hierarchically organized or governed by hierarchical semantics, ranging from recommendation systems to computer vision. The quality of hyperbolic embeddings is tightly coupled to the structure of the input hierarchy, which is often derived from knowledge graphs or ontologies. Recent work has uncovered that for an optimal hyperbolic embedding, a high branching factor and single inheritance are key, while embedding algorithms are robust to imbalance and hierarchy size. To assist knowledge engineers in reorganizing hierarchical knowledge, this paper investigates whether Large Language Models (LLMs) have the ability to automatically restructure hierarchies to meet these criteria. We propose a prompt-based approach to transform existing hierarchies using LLMs, guided by known desiderata for hyperbolic embeddings. Experiments on 16 diverse hierarchies show that LLM-restructured hierarchies consistently yield higher-quality hyperbolic embeddings across several standard embedding quality metrics. Moreover, we show how LLM-guided hierarchy restructuring enables explainable reorganizations, providing justifications to knowledge engineers. --- ### Cryptocurrency Portfolio Management with Reinforcement Learning: Soft Actor--Critic and Deep Deterministic Policy Gradient Algorithms Authors: Kamal Paykan Published: 2025-11-16 Categories: q-fin.CP, cs.LG arXiv: https://arxiv.org/abs/2511.20678v1 This paper proposes a reinforcement learning--based framework for cryptocurrency portfolio management using the Soft Actor--Critic (SAC) and Deep Deterministic Policy Gradient (DDPG) algorithms. Traditional portfolio optimization methods often struggle to adapt to the highly volatile and nonlinear dynamics of cryptocurrency markets. To address this, we design an agent that learns continuous trading actions directly from historical market data through interaction with a simulated trading environment. The agent optimizes portfolio weights to maximize cumulative returns while minimizing downside risk and transaction costs. Experimental evaluations on multiple cryptocurrencies demonstrate that the SAC and DDPG agents outperform baseline strategies such as equal-weighted and mean--variance portfolios. The SAC algorithm, with its entropy-regularized objective, shows greater stability and robustness in noisy market conditions compared to DDPG. These results highlight the potential of deep reinforcement learning for adaptive and data-driven portfolio management in cryptocurrency markets. --- ### Prompt Engineering Techniques for Context-dependent Text-to-SQL in Arabic Authors: Saleh Almohaimeed, May Alsofyani, Saad Almohaimeed, Mansour Al Ghanim, Liqiang Wang Published: 2025-11-16 Categories: cs.CL, cs.DB arXiv: https://arxiv.org/abs/2511.20677v1 In recent years, the task of cross-domain, context-dependent text-to-SQL has received significant attention. Enables users with no prior knowledge of SQL to have a conversation with databases using natural language. However, most of the available datasets and research have been conducted in English, along with some work in Chinese. To this date, no effort has been made to address this task in the Arabic language. In this paper, we introduce Ar-SParC, the first Arabic cross-domain, context-dependent text-to-SQL dataset. The dataset consists of 3,450 sequences of interrelated questions, each sequence containing an average of approximately three questions, which results in a total of 10225 questions along with their corresponding SQL queries. We conducted 40 experiments on the Ar-SParC dataset using two large language models, GPT-3.5-turbo and GPT-4.5-turbo, applying 10 different prompt engineering techniques, including four question representation methods and six in-context learning techniques. Furthermore, we developed a novel approach named GAT corrector, which enhanced the performance across all 40 experiments, yielding an average improvement of 1.9% in execution accuracy (EX) and 1.9% in interaction accuracy (IX) under zero-shot settings, and an average increase of 1.72% EX and 0.92% IX under in-context learning settings. Finally, we conducted an ablation study with two more experiments to explain why the GAT corrector outperformed the previous GAT verifier technique, particularly for the Arabic language. --- ### Llamazip: Leveraging LLaMA for Lossless Text Compression and Training Dataset Detection Authors: Sören Dréano, Derek Molloy, Noel Murphy Published: 2025-11-16 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2511.17589v1 This work introduces Llamazip, a novel lossless text compression algorithm based on the predictive capabilities of the LLaMA3 language model. Llamazip achieves significant data reduction by only storing tokens that the model fails to predict, optimizing storage efficiency without compromising data integrity. Key factors affecting its performance, including quantization and context window size, are analyzed, revealing their impact on compression ratios and computational requirements. Beyond compression, Llamazip demonstrates the potential to identify whether a document was part of the training dataset of a language model. This capability addresses critical concerns about data provenance, intellectual property, and transparency in language model training. --- ### Emotion and Intention Guided Multi-Modal Learning for Sticker Response Selection Authors: Yuxuan Hu, Jian Chen, Yuhao Wang, Zixuan Li, Jing Xiong, Pengyue Jia, Wei Wang, Chengming Li, Xiangyu Zhao Published: 2025-11-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.17587v1 Stickers are widely used in online communication to convey emotions and implicit intentions. The Sticker Response Selection (SRS) task aims to select the most contextually appropriate sticker based on the dialogue. However, existing methods typically rely on semantic matching and model emotional and intentional cues separately, which can lead to mismatches when emotions and intentions are misaligned. To address this issue, we propose Emotion and Intention Guided Multi-Modal Learning (EIGML). This framework is the first to jointly model emotion and intention, effectively reducing the bias caused by isolated modeling and significantly improving selection accuracy. Specifically, we introduce Dual-Level Contrastive Framework to perform both intra-modality and inter-modality alignment, ensuring consistent representation of emotional and intentional features within and across modalities. In addition, we design an Intention-Emotion Guided Multi-Modal Fusion module that integrates emotional and intentional information progressively through three components: Emotion-Guided Intention Knowledge Selection, Intention-Emotion Guided Attention Fusion, and Similarity-Adjusted Matching Mechanism. This design injects rich, effective information into the model and enables a deeper understanding of the dialogue, ultimately enhancing sticker selection performance. Experimental results on two public SRS datasets show that EIGML consistently outperforms state-of-the-art baselines, achieving higher accuracy and a better understanding of emotional and intentional features. Code is provided in the supplementary materials. --- ### Hierarchical Adaptive Consensus Network: A Dynamic Framework for Scalable Consensus in Collaborative Multi-Agent AI Systems Authors: Rathin Chandra Shit, Sharmila Subudhi Published: 2025-11-16 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2511.17586v1 The consensus strategies used in collaborative multi-agent systems (MAS) face notable challenges related to adaptability, scalability, and convergence certainties. These approaches, including structured workflows, debate models, and iterative voting, often lead to communication bottlenecks, stringent decision-making processes, and delayed responses in solving complex and evolving tasks. This article introduces a three-tier architecture, the Hierarchical Adaptive Consensus Network (\hacn), which suggests various consensus policies based on task characterization and agent performance metrics. The first layer collects the confidence-based voting outcomes of several local agent clusters. In contrast, the second level facilitates inter-cluster communication through cross-clustered partial knowledge sharing and dynamic timeouts. The third layer provides system-wide coordination and final arbitration by employing a global orchestration framework with adaptable decision rules. The proposed model achieves $\bigO(n)$ communication complexity, as opposed to the $\bigO(n^2)$ complexity of the existing fully connected MAS. Experiments performed in a simulated environment yielded a 99.9\% reduction in communication overhead during consensus convergence. Furthermore, the proposed approach ensures consensus convergence through hierarchical escalation and dynamic adaptation for a wide variety of complicated tasks. --- ### PaSE: Prototype-aligned Calibration and Shapley-based Equilibrium for Multimodal Sentiment Analysis Authors: Kang He, Boyu Chen, Yuzhe Ding, Fei Li, Chong Teng, Donghong Ji Published: 2025-11-16 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.17585v2 Multimodal Sentiment Analysis (MSA) seeks to understand human emotions by integrating textual, acoustic, and visual signals. Although multimodal fusion is designed to leverage cross-modal complementarity, real-world scenarios often exhibit modality competition: dominant modalities tend to overshadow weaker ones, leading to suboptimal performance. In this paper, we propose PaSE, a novel Prototype-aligned Calibration and Shapley-optimized Equilibrium framework, which enhances collaboration while explicitly mitigating modality competition. PaSE first applies Prototype-guided Calibration Learning (PCL) to refine unimodal representations and align them through an Entropic Optimal Transport mechanism that ensures semantic consistency. To further stabilize optimization, we introduce a Dual-Phase Optimization strategy. A prototype-gated fusion module is first used to extract shared representations, followed by Shapley-based Gradient Modulation (SGM), which adaptively adjusts gradients according to the contribution of each modality. Extensive experiments on IEMOCAP, MOSI, and MOSEI confirm that PaSE achieves the superior performance and effectively alleviates modality competition. --- ### LLM-Powered Text-Attributed Graph Anomaly Detection via Retrieval-Augmented Reasoning Authors: Haoyan Xu, Ruizhi Qian, Zhengtao Yao, Ziyi Liu, Li Li, Yuqi Li, Yanshu Li, Wenqing Zheng, Daniele Rosa, Daniel Barcklow, Senthil Kumar, Jieyu Zhao et al. Published: 2025-11-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.17584v1 Anomaly detection on attributed graphs plays an essential role in applications such as fraud detection, intrusion monitoring, and misinformation analysis. However, text-attributed graphs (TAGs), in which node information is expressed in natural language, remain underexplored, largely due to the absence of standardized benchmark datasets. In this work, we introduce TAG-AD, a comprehensive benchmark for anomaly node detection on TAGs. TAG-AD leverages large language models (LLMs) to generate realistic anomalous node texts directly in the raw text space, producing anomalies that are semantically coherent yet contextually inconsistent and thus more reflective of real-world irregularities. In addition, TAG-AD incorporates multiple other anomaly types, enabling thorough and reproducible evaluation of graph anomaly detection (GAD) methods. With these datasets, we further benchmark existing unsupervised GNN-based GAD methods as well as zero-shot LLMs for GAD. As part of our zero-shot detection setup, we propose a retrieval-augmented generation (RAG)-assisted, LLM-based zero-shot anomaly detection framework. The framework mitigates reliance on brittle, hand-crafted prompts by constructing a global anomaly knowledge base and distilling it into reusable analysis frameworks. Our experimental results reveal a clear division of strengths: LLMs are particularly effective at detecting contextual anomalies, whereas GNN-based methods remain superior for structural anomaly detection. Moreover, RAG-assisted prompting achieves performance comparable to human-designed prompts while eliminating manual prompt engineering, underscoring the practical value of our RAG-assisted zero-shot LLM anomaly detection framework. --- ### How Language Directions Align with Token Geometry in Multilingual LLMs Authors: JaeSeong Kim, Suan Lee Published: 2025-11-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.16693v1 Multilingual LLMs demonstrate strong performance across diverse languages, yet there has been limited systematic analysis of how language information is structured within their internal representation space and how it emerges across layers. We conduct a comprehensive probing study on six multilingual LLMs, covering all 268 transformer layers, using linear and nonlinear probes together with a new Token--Language Alignment analysis to quantify the layer-wise dynamics and geometric structure of language encoding. Our results show that language information becomes sharply separated in the first transformer block (+76.4$\pm$8.2 percentage points from Layer 0 to 1) and remains almost fully linearly separable throughout model depth. We further find that the alignment between language directions and vocabulary embeddings is strongly tied to the language composition of the training data. Notably, Chinese-inclusive models achieve a ZH Match@Peak of 16.43\%, whereas English-centric models achieve only 3.90\%, revealing a 4.21$\times$ structural imprinting effect. These findings indicate that multilingual LLMs distinguish languages not by surface script features but by latent representational structures shaped by the training corpus. Our analysis provides practical insights for data composition strategies and fairness in multilingual representation learning. All code and analysis scripts are publicly available at: https://github.com/thisiskorea/How-Language-Directions-Align-with-Token-Geometry-in-Multilingual-LLMs. --- ### Reproducibility Report: Test-Time Training on Nearest Neighbors for Large Language Models Authors: Boyang Zhou, Johan Lindqvist, Lindsey Li Published: 2025-11-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.16691v1 We reproduce the central claims of Test-Time Training on Nearest Neighbors for Large Language Models (Hardt and Sun, 2024), which proposes adapting a language model at inference time by fine-tuning on retrieved nearest-neighbor sequences. Using pretrained RoBERTa embeddings indexed with Faiss, we retrieve 20 neighbors per test input and apply one gradient update per neighbor across GPT-2 (117M, 774M), GPT-Neo (1.3B), and R1-Distilled-Qwen2.5-1.5B. Our experiments confirm that test-time training significantly reduces perplexity and bits-per-byte metrics across diverse domains from The Pile, with the largest improvements in structured or specialized datasets such as GitHub and EuroParl. We further validate that models not pretrained on The Pile benefit more from this adaptation than models already trained on similar data, allowing smaller models to approach the performance of larger ones. Due to infrastructure limitations, we introduce a memory-efficient retrieval implementation that loads only required line offsets rather than entire files, reducing RAM requirements from over 128 GB per server to 32 GB. We also extend the original study by evaluating R1-Distilled-Qwen2.5-1.5B, showing that test-time training yields consistent gains even for modern reasoning-optimized architectures. Overall, our results support the robustness and generality of nearest-neighbor test-time training while highlighting practical considerations for reproducing large-scale retrieval-augmented adaptation. --- ### AI Text Detectors and the Misclassification of Slightly Polished Arabic Text Authors: Saleh Almohaimeed, Saad Almohaimeed, Mousa Jari, Khaled A. Alobaid, Fahad Alotaibi Published: 2025-11-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.16690v2 Many AI detection models have been developed to counter the presence of articles created by artificial intelligence (AI). However, if a human-authored article is slightly polished by AI, a shift will occur in the borderline decision of these AI detection models, leading them to consider it as AI-generated article. This misclassification may result in falsely accusing authors of AI plagiarism and harm the credibility of AI detectors. In English, some efforts were made to meet this challenge, but not in Arabic. In this paper, we generated two datasets. The first dataset contains 800 Arabic articles, half AI-generated and half human-authored. We used it to evaluate 14 Large Language models (LLMs) and commercial AI detectors to assess their ability in distinguishing between human-authored and AI-generated articles. The best 8 models were chosen to act as detectors for our primary concern, which is whether they would consider slightly polished human-authored text as AI-generated. The second dataset, Ar-APT, contains 400 Arabic human-authored articles polished by 10 LLMs using 4 polishing settings, totaling 16400 samples. We use it to evaluate the 8 nominated models and determine whether slight polishing will affect their performance. The results reveal that all AI detectors incorrectly attribute a significant number of articles to AI. The best performing LLM, Claude-4 Sonnet, achieved 83.51\%, its performance decreased to 57.63\% for articles slightly polished by LLaMA-3. Whereas the best performing commercial model, originality.AI, achieves 92\% accuracy, dropped to 12\% for articles slightly polished by Mistral or Gemma-3. --- ### Opinion Mining and Analysis Using Hybrid Deep Neural Networks Authors: Adel Hidri, Suleiman Ali Alsaif, Muteeb Alahmari, Eman AlShehri, Minyar Sassi Hidri Published: 2025-11-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.14796v1 Understanding customer attitudes has become a critical component of decision-making due to the growing influence of social media and e-commerce. Text-based opinions are the most structured, hence playing an important role in sentiment analysis. Most of the existing methods, which include lexicon-based approaches and traditional machine learning techniques, are insufficient for handling contextual nuances and scalability. While the latter has limitations in model performance and generalization, deep learning (DL) has achieved improvement, especially on semantic relationship capturing with recurrent neural networks (RNNs) and convolutional neural networks (CNNs). The aim of the study is to enhance opinion mining by introducing a hybrid deep neural network model that combines a bidirectional gated recurrent unit (BGRU) and long short-term memory (LSTM) layers to improve sentiment analysis, particularly addressing challenges such as contextual nuance, scalability, and class imbalance. To substantiate the efficacy of the proposed model, we conducted comprehensive experiments utilizing benchmark datasets, encompassing IMDB movie critiques and Amazon product evaluations. The introduced hybrid BGRULSTM (HBGRU-LSTM) architecture attained a testing accuracy of 95%, exceeding the performance of traditional DL frameworks such as LSTM (93.06%), CNN+LSTM (93.31%), and GRU+LSTM (92.20%). Moreover, our model exhibited a noteworthy enhancement in recall for negative sentiments, escalating from 86% (unbalanced dataset) to 96% (balanced dataset), thereby ensuring a more equitable and just sentiment classification. Furthermore, the model diminished misclassification loss from 20.24% for unbalanced to 13.3% for balanced dataset, signifying enhanced generalization and resilience. --- ### Modeling Fairness in Recruitment AI via Information Flow Authors: Mattias Brännström, Themis Dimitra Xanthopoulou, Lili Jiang Published: 2025-11-16 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2511.13793v1 Avoiding bias and understanding the real-world consequences of AI-supported decision-making are critical to address fairness and assign accountability. Existing approaches often focus either on technical aspects, such as datasets and models, or on high-level socio-ethical considerations - rarely capturing how these elements interact in practice. In this paper, we apply an information flow-based modeling framework to a real-world recruitment process that integrates automated candidate matching with human decision-making. Through semi-structured stakeholder interviews and iterative modeling, we construct a multi-level representation of the recruitment pipeline, capturing how information is transformed, filtered, and interpreted across both algorithmic and human components. We identify where biases may emerge, how they can propagate through the system, and what downstream impacts they may have on candidates. This case study illustrates how information flow modeling can support structured analysis of fairness risks, providing transparency across complex socio-technical systems. --- ### XAI-Driven Deep Learning for Protein Sequence Functional Group Classification Authors: Pratik Chakraborty, Aryan Bhargava Published: 2025-11-16 Categories: q-bio.QM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.13791v1 Proteins perform essential biological functions, and accurate classification of their sequences is critical for understanding structure-function relationships, enzyme mechanisms, and molecular interactions. This study presents a deep learning-based framework for functional group classification of protein sequences derived from the Protein Data Bank (PDB). Four architectures were implemented: Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), CNN-BiLSTM hybrid, and CNN with Attention. Each model was trained using k-mer integer encoding to capture both local and long-range dependencies. Among these, the CNN achieved the highest validation accuracy of 91.8%, demonstrating the effectiveness of localized motif detection. Explainable AI techniques, including Grad-CAM and Integrated Gradients, were applied to interpret model predictions and identify biologically meaningful sequence motifs. The discovered motifs, enriched in histidine, aspartate, glutamate, and lysine, represent amino acid residues commonly found in catalytic and metal-binding regions of transferase enzymes. These findings highlight that deep learning models can uncover functionally relevant biochemical signatures, bridging the gap between predictive accuracy and biological interpretability in protein sequence analysis. --- ### GeoPl@ntNet: A Platform for Exploring Essential Biodiversity Variables Authors: Lukas Picek, César Leblanc, Alexis Joly, Pierre Bonnet, Rémi Palard, Maximilien Servajean Published: 2025-11-16 Categories: q-bio.QM, cs.AI arXiv: https://arxiv.org/abs/2511.13790v2 This paper describes GeoPl@ntNet, an interactive web application designed to make Essential Biodiversity Variables accessible and understandable to everyone through dynamic maps and fact sheets. Its core purpose is to allow users to explore high-resolution AI-generated maps of species distributions, habitat types, and biodiversity indicators across Europe. These maps, developed through a cascading pipeline involving convolutional neural networks and large language models, provide an intuitive yet information-rich interface to better understand biodiversity, with resolutions as precise as 50x50 meters. The website also enables exploration of specific regions, allowing users to select areas of interest on the map (e.g., urban green spaces, protected areas, or riverbanks) to view local species and their coverage. Additionally, GeoPl@ntNet generates comprehensive reports for selected regions, including insights into the number of protected species, invasive species, and endemic species. --- ### Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks Authors: Haotian Jin, Yang Li, Haihui Fan, Lin Shen, Xiangfang Li, Bo Li Published: 2025-11-16 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.13789v1 Backdoor attacks pose a serious threat to the security of large language models (LLMs), causing them to exhibit anomalous behavior under specific trigger conditions. The design of backdoor triggers has evolved from fixed triggers to dynamic or implicit triggers. This increased flexibility in trigger design makes it challenging for defenders to identify their specific forms accurately. Most existing backdoor defense methods are limited to specific types of triggers or rely on an additional clean model for support. To address this issue, we propose a backdoor detection method based on attention similarity, enabling backdoor detection without prior knowledge of the trigger. Our study reveals that models subjected to backdoor attacks exhibit unusually high similarity among attention heads when exposed to triggers. Based on this observation, we propose an attention safety alignment approach combined with head-wise fine-tuning to rectify potentially contaminated attention heads, thereby effectively mitigating the impact of backdoor attacks. Extensive experimental results demonstrate that our method significantly reduces the success rate of backdoor attacks while preserving the model's performance on downstream tasks. --- ### Scaling Patterns in Adversarial Alignment: Evidence from Multi-LLM Jailbreak Experiments Authors: Samuel Nathanson, Rebecca Williams, Cynthia Matuszek Published: 2025-11-16 Categories: cs.LG, cs.AI, cs.CL, cs.CR, cs.MA arXiv: https://arxiv.org/abs/2511.13788v2 Large language models (LLMs) increasingly operate in multi-agent and safety-critical settings, raising open questions about how their vulnerabilities scale when models interact adversarially. This study examines whether larger models can systematically jailbreak smaller ones - eliciting harmful or restricted behavior despite alignment safeguards. Using standardized adversarial tasks from JailbreakBench, we simulate over 6,000 multi-turn attacker-target exchanges across major LLM families and scales (0.6B-120B parameters), measuring both harm score and refusal behavior as indicators of adversarial potency and alignment integrity. Each interaction is evaluated through aggregated harm and refusal scores assigned by three independent LLM judges, providing a consistent, model-based measure of adversarial outcomes. Aggregating results across prompts, we find a strong and statistically significant correlation between mean harm and the logarithm of the attacker-to-target size ratio (Pearson r = 0.51, p < 0.001; Spearman rho = 0.52, p < 0.001), indicating that relative model size correlates with the likelihood and severity of harmful completions. Mean harm score variance is higher across attackers (0.18) than across targets (0.10), suggesting that attacker-side behavioral diversity contributes more to adversarial outcomes than target susceptibility. Attacker refusal frequency is strongly and negatively correlated with harm (rho = -0.93, p < 0.001), showing that attacker-side alignment mitigates harmful responses. These findings reveal that size asymmetry influences robustness and provide exploratory evidence for adversarial scaling patterns, motivating more controlled investigations into inter-model alignment and safety. --- ### Exploring Transferability of Self-Supervised Learning by Task Conflict Calibration Authors: Huijie Guo, Jingyao Wang, Peizheng Guo, Xingchen Shen, Changwen Zheng, Wenwen Qiang Published: 2025-11-16 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2511.13787v1 In this paper, we explore the transferability of SSL by addressing two central questions: (i) what is the representation transferability of SSL, and (ii) how can we effectively model this transferability? Transferability is defined as the ability of a representation learned from one task to support the objective of another. Inspired by the meta-learning paradigm, we construct multiple SSL tasks within each training batch to support explicitly modeling transferability. Based on empirical evidence and causal analysis, we find that although introducing task-level information improves transferability, it is still hindered by task conflict. To address this issue, we propose a Task Conflict Calibration (TC$^2$) method to alleviate the impact of task conflict. Specifically, it first splits batches to create multiple SSL tasks, infusing task-level information. Next, it uses a factor extraction network to produce causal generative factors for all tasks and a weight extraction network to assign dedicated weights to each sample, employing data reconstruction, orthogonality, and sparsity to ensure effectiveness. Finally, TC$^2$ calibrates sample representations during SSL training and integrates into the pipeline via a two-stage bi-level optimization framework to boost the transferability of learned representations. Experimental results on multiple downstream tasks demonstrate that our method consistently improves the transferability of SSL models. --- ### CellStream: Dynamical Optimal Transport Informed Embeddings for Reconstructing Cellular Trajectories from Snapshots Data Authors: Yue Ling, Peiqi Zhang, Zhenyi Zhang, Peijie Zhou Published: 2025-11-16 Categories: q-bio.GN, cs.LG arXiv: https://arxiv.org/abs/2511.13786v1 Single-cell RNA sequencing (scRNA-seq), especially temporally resolved datasets, enables genome-wide profiling of gene expression dynamics at single-cell resolution across discrete time points. However, current technologies provide only sparse, static snapshots of cell states and are inherently influenced by technical noise, complicating the inference and representation of continuous transcriptional dynamics. Although embedding methods can reduce dimensionality and mitigate technical noise, the majority of existing approaches typically treat trajectory inference separately from embedding construction, often neglecting temporal structure. To address this challenge, here we introduce CellStream, a novel deep learning framework that jointly learns embedding and cellular dynamics from single-cell snapshot data by integrating an autoencoder with unbalanced dynamical optimal transport. Compared to existing methods, CellStream generates dynamics-informed embeddings that robustly capture temporal developmental processes while maintaining high consistency with the underlying data manifold. We demonstrate CellStream's effectiveness on both simulated datasets and real scRNA-seq data, including spatial transcriptomics. Our experiments indicate significant quantitative improvements over state-of-the-art methods in representing cellular trajectories with enhanced temporal coherence and reduced noise sensitivity. Overall, CellStream provides a new tool for learning and representing continuous streams from the noisy, static snapshots of single-cell gene expression. --- ### Quantifying Distribution Shift in Traffic Signal Control with Histogram-Based GEH Distance Authors: Federico Taschin, Ozan K. Tonguz Published: 2025-11-16 Categories: eess.SY, cs.AI arXiv: https://arxiv.org/abs/2511.13785v1 Traffic signal control algorithms are vulnerable to distribution shift, where performance degrades under traffic conditions that differ from those seen during design or training. This paper introduces a principled approach to quantify distribution shift by representing traffic scenarios as demand histograms and comparing them with a GEH-based distance function. The method is policy-independent, interpretable, and leverages a widely used traffic engineering statistic. We validate the approach on 20 simulated scenarios using both a NEMA actuated controller and a reinforcement learning controller (FRAP++). Results show that larger scenario distances consistently correspond to increased travel time and reduced throughput, with particularly strong explanatory power for learning-based control. Overall, this method can predict performance degradation under distribution shift better than previously published techniques. These findings highlight the utility of the proposed framework for benchmarking, training regime design, and monitoring in adaptive traffic signal control. --- ### Temporal Object-Aware Vision Transformer for Few-Shot Video Object Detection Authors: Yogesh Kumar, Anand Mishra Published: 2025-11-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.13784v1 Few-shot Video Object Detection (FSVOD) addresses the challenge of detecting novel objects in videos with limited labeled examples, overcoming the constraints of traditional detection methods that require extensive training data. This task presents key challenges, including maintaining temporal consistency across frames affected by occlusion and appearance variations, and achieving novel object generalization without relying on complex region proposals, which are often computationally expensive and require task-specific training. Our novel object-aware temporal modeling approach addresses these challenges by incorporating a filtering mechanism that selectively propagates high-confidence object features across frames. This enables efficient feature progression, reduces noise accumulation, and enhances detection accuracy in a few-shot setting. By utilizing few-shot trained detection and classification heads with focused feature propagation, we achieve robust temporal consistency without depending on explicit object tube proposals. Our approach achieves performance gains, with AP improvements of 3.7% (FSVOD-500), 5.3% (FSYTV-40), 4.3% (VidOR), and 4.5 (VidVRD) in the 5-shot setting. Further results demonstrate improvements in 1-shot, 3-shot, and 10-shot configurations. We make the code public at: https://github.com/yogesh-iitj/fs-video-vit --- ### Imagine in Space: Exploring the Frontier of Spatial Intelligence and Reasoning Efficiency in Vision Language Models Authors: Xiaoxing Lian, Aidong Yang, Jun Zhu, Peng Wang, Yue Zhang Published: 2025-11-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.13782v1 Large language models (LLMs) and vision language models (VLMs), such as DeepSeek R1,OpenAI o3, and Gemini 2.5 Pro, have demonstrated remarkable reasoning capabilities across logical inference, problem solving, and decision making. However, spatial reasoning:a fundamental component of human cognition that includes mental rotation, navigation, and spatial relationship comprehension remains a significant challenge for current advanced VLMs. We hypothesize that imagination, the internal simulation of spatial states, is the dominant reasoning mechanism within a spatial world model. To test this hypothesis and systematically probe current VLM spatial reasoning mechanisms, we introduce SpatiaLite, a fully synthetic benchmark that jointly measures spatial reasoning accuracy and reasoning efficiency. Comprehensive experiments reveal three key findings. First, advanced VLMs predominantly rely on linguistic representations for reasoning and imagination, resulting in significant deficiencies on visual centric tasks that demand perceptual spatial relations and 3D geometry transformations such as mental rotation or projection prediction. Second, advanced VLMs exhibit severe inefficiency in their current spatial reasoning mechanisms, with token usage growing rapidly as transformation complexity increases. Third, we propose an Imagery Driven Framework (IDF) for data synthesis and training, which can implicitly construct an internal world model that is critical for spatial reasoning in VLMs. Building on SpatiaLite, this work delineates the spatial reasoning limits and patterns of advanced VLMs, identifies key shortcomings, and informs future advances --- ### Self-Attention as Distributional Projection: A Unified Interpretation of Transformer Architecture Authors: Nihal Mehta Published: 2025-11-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.13780v1 This paper presents a mathematical interpretation of self-attention by connecting it to distributional semantics principles. We show that self-attention emerges from projecting corpus-level co-occurrence statistics into sequence context. Starting from the co-occurrence matrix underlying GloVe embeddings, we demonstrate how the projection naturally captures contextual influence, with the query-key-value mechanism arising as the natural asymmetric extension for modeling directional relationships. Positional encodings and multi-head attention then follow as structured refinements of this same projection principle. Our analysis demonstrates that the Transformer architecture's particular algebraic form follows from these projection principles rather than being an arbitrary design choice. --- ### Semantic Multiplexing Authors: Mohammad Abdi, Francesca Meneghello, Francesco Restuccia Published: 2025-11-16 Categories: cs.DC, cs.AI, cs.LG, cs.NI, eess.IV arXiv: https://arxiv.org/abs/2511.13779v1 Mobile devices increasingly require the parallel execution of several computing tasks offloaded at the wireless edge. Existing communication systems only support parallel transmissions at the bit level, which fundamentally limits the number of tasks that can be concurrently processed. To address this bottleneck, this paper introduces the new concept of Semantic Multiplexing. Our approach shifts stream multiplexing from bits to tasks by merging multiple task-related compressed representations into a single semantic representation. As such, Semantic Multiplexing can multiplex more tasks than the number of physical channels without adding antennas or widening bandwidth by extending the effective degrees of freedom at the semantic layer, without contradicting Shannon capacity rules. We have prototyped Semantic Multiplexing on an experimental testbed with Jetson Orin Nano and millimeter-wave software-defined radios and tested its performance on image classification and sentiment analysis while comparing to several existing baselines in semantic communications. Our experiments demonstrate that Semantic Multiplexing allows jointly processing multiple tasks at the semantic level while maintaining sufficient task accuracy. For example, image classification accuracy drops by less than 4% when increasing from 2 to 8 the number of tasks multiplexed over a 4$\times$4 channel. Semantic Multiplexing reduces latency, energy consumption, and communication load respectively by up to 8$\times$, 25$\times$, and 54$\times$ compared to the baselines while keeping comparable performance. We pledge to publicly share the complete software codebase and the collected datasets for reproducibility. --- ### Benign Overfitting in Linear Classifiers with a Bias Term Authors: Yuta Kondo Published: 2025-11-16 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.12840v2 Overparameterized models often generalize well even when they interpolate noisy training data. This is known as benign overfitting. For linear classification, Hashimoto et al. (2025) analyzed the phenomenon under a broad class of mixture distributions, but only for homogeneous classifiers without a bias term. We extend their framework to classifiers with an intercept. Benign overfitting still occurs, but the intercept perturbs the normalized Gram matrix of the noise and creates extra constraints on the covariance. These constraints are strongest with label noise. Their effect depends on the covariance: under isotropic noise they are dominated by the homogeneous conditions, while in anisotropic or noisy regimes they can raise the dimensionality needed for benign generalization. Thus the bias term changes the theory in some covariance regimes and leaves the asymptotic thresholds unchanged in others. --- ### Connectivity-Guided Sparsification of 2-FWL GNNs: Preserving Full Expressivity with Improved Efficiency Authors: Rongqin Chen, Fan Mo, Pak Lon Ip, Shenghui Zhang, Dan Wu, Ye Li, Leong Hou U Published: 2025-11-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.12838v1 Higher-order Graph Neural Networks (HOGNNs) based on the 2-FWL test achieve superior expressivity by modeling 2- and 3-node interactions, but at $\mathcal{O}(n^3)$ computational cost. However, this computational burden is typically mitigated by existing efficiency methods at the cost of reduced expressivity. We propose \textbf{Co-Sparsify}, a connectivity-aware sparsification framework that eliminates \emph{provably redundant} computations while preserving full 2-FWL expressive power. Our key insight is that 3-node interactions are expressively necessary only within \emph{biconnected components} -- maximal subgraphs where every pair of nodes lies on a cycle. Outside these components, structural relationships can be fully captured via 2-node message passing or global readout, rendering higher-order modeling unnecessary. Co-Sparsify restricts 2-node message passing to connected components and 3-node interactions to biconnected ones, removing computation without approximation or sampling. We prove that Co-Sparsified GNNs are as expressive as the 2-FWL test. Empirically, on PPGN, Co-Sparsify matches or exceeds accuracy on synthetic substructure counting tasks and achieves state-of-the-art performance on real-world benchmarks (ZINC, QM9). This study demonstrates that high expressivity and scalability are not mutually exclusive: principled, topology-guided sparsification enables powerful, efficient GNNs with theoretical guarantees. ---