# Research Papers — 2026-03 · bundle page 165 of 243 > Full-text markdown of papers #8201–8250 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/165 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/164.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/166.md) ### What do near-optimal learning rate schedules look like? Authors: Hiroki Naganuma, Atish Agarwala, Priya Kasimbeg, George E. Dahl Published: 2026-03-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.10301v2 A basic unanswered question in neural network training is: what is the best learning rate schedule shape for a given workload? The choice of learning rate schedule is a key factor in the success or failure of the training process, but beyond having some kind of warmup and decay, there is no consensus on what makes a good schedule shape. To answer this question, we designed a search procedure to find the best shapes within a parameterized schedule family. Our approach factors out the schedule shape from the base learning rate, which otherwise would dominate cross-schedule comparisons. We applied our search procedure to a variety of schedule families on three workloads: linear regression, image classification on CIFAR-10, and small-scale language modeling on Wikitext103. We showed that our search procedure indeed generally found near-optimal schedules. We found that warmup and decay are robust features of good schedules, and that commonly used schedule families are not optimal on these workloads. Finally, we explored how the outputs of our shape search depend on other optimization hyperparameters, and found that weight decay can have a strong effect on the optimal schedule shape. To the best of our knowledge, our results represent the most comprehensive results on near-optimal schedule shapes for deep neural network training, to date. --- ### From Imitation to Intuition: Intrinsic Reasoning for Open-Instance Video Classification Authors: Ke Zhang, Xiangchen Zhao, Yunjie Tian, Jiayu Zheng, Vishal M. Patel, Di Fu Published: 2026-03-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.10300v3 Conventional video classification models, acting as effective imitators, excel in scenarios with homogeneous data distributions. However, real-world applications often present an open-instance challenge, where intra-class variations are vast and complex, beyond existing benchmarks. While traditional video encoder models struggle to fit these diverse distributions, vision-language models (VLMs) offer superior generalization but have not fully leveraged their reasoning capabilities (intuition) for such tasks. In this paper, we bridge this gap with an intrinsic reasoning framework that evolves open-instance video classification from imitation to intuition. Our approach, namely DeepIntuit, begins with a cold-start supervised alignment to initialize reasoning capability, followed by refinement using Group Relative Policy Optimization (GRPO) to enhance reasoning coherence through reinforcement learning. Crucially, to translate this reasoning into accurate classification, DeepIntuit then introduces an intuitive calibration stage. In this stage, a classifier is trained on this intrinsic reasoning traces generated by the refined VLM, ensuring stable knowledge transfer without distribution mismatch. Extensive experiments demonstrate that for open-instance video classification, DeepIntuit benefits significantly from transcending simple feature imitation and evolving toward intrinsic reasoning. Our project is available at https://bwgzk-keke.github.io/DeepIntuit/. --- ### Regime-aware financial volatility forecasting via in-context learning Authors: Saba Asaad, Shayan Mohajer Hamidi, Ali Bereyhi Published: 2026-03-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.10299v1 This work introduces a regime-aware in-context learning framework that leverages large language models (LLMs) for financial volatility forecasting under nonstationary market conditions. The proposed approach deploys pretrained LLMs to reason over historical volatility patterns and adjust their predictions without parameter fine-tuning. We develop an oracle-guided refinement procedure that constructs regime-aware demonstrations from training data. An LLM is then deployed as an in-context learner that predicts the next-step volatility from the input sequence using demonstrations sampled conditional to the estimated market label. This conditional sampling strategy enables the LLM to adapt its predictions to regime-dependent volatility dynamics through contextual reasoning alone. Experiments with multiple financial datasets show that the proposed regime-aware in-context learning framework outperforms both classical volatility forecasting approaches and direct one-shot learning, especially during high-volatility periods. --- ### GaLoRA: Parameter-Efficient Graph-Aware LLMs for Node Classification Authors: Mayur Choudhary, Saptarshi Sengupta, Katerina Potika Published: 2026-03-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.10298v1 The rapid rise of large language models (LLMs) and their ability to capture semantic relationships has led to their adoption in a wide range of applications. Text-attributed graphs (TAGs) are a notable example where LLMs can be combined with Graph Neural Networks to improve the performance of node classification. In TAGs, each node is associated with textual content and such graphs are commonly seen in various domains such as social networks, citation graphs, recommendation systems, etc. Effectively learning from TAGs would enable better representations of both structural and textual representations of the graph and improve decision-making in relevant domains. We present GaLoRA, a parameter-efficient framework that integrates structural information into LLMs. GaLoRA demonstrates competitive performance on node classification tasks with TAGs, performing on par with state-of-the-art models with just 0.24% of the parameter count required by full LLM fine-tuning. We experiment with three real-world datasets to showcase GaLoRA's effectiveness in combining structural and semantical information on TAGs. --- ### Simulation-in-the-Reasoning (SiR): A Conceptual Framework for Empirically Grounded AI in Autonomous Transportation Authors: Wuping Xin Published: 2026-03-11 Categories: eess.SY, cs.AI arXiv: https://arxiv.org/abs/2603.10294v1 Large Language Models (LLMs) have advanced reasoning through techniques like Chain-of-Thought (CoT). However, their reasoning largely re-mains textual and hypothetical, lacking empirical grounding in complex, dynamic domains like transportation. This paper introduces Simulation-in-the-Reasoning (SiR), a novel conceptual framework that embeds domain-specific simulators directly into the LLM reasoning loop. By treating intermediate reasoning steps as executable simulation experiments, SiR transforms LLM reasoning from narrative plausibility into a falsifiable, hypothesis-simulate-analyze workflow. We discuss applications, where LLM can formulate Intelligent Transport System (ITS) strategy hypotheses, invoke a traffic simulator via the Model Context Protocol (MCP), evaluate results under different demand patterns, and refine strategies through verification and aggregation. While implementing the framework is part of our ongoing work, this paper primarily establishes the conceptual foundation, discusses design considerations like API granularity, and outlines the vision of SiR as a cornerstone for interactive transportation digital twins. We argue that SiR represents a critical step towards trustworthy, empirically-validated AI for autonomous transportation systems. --- ### Hybrid Self-evolving Structured Memory for GUI Agents Authors: Sibo Zhu, Wenyi Wu, Kun Zhou, Stephen Wang, Biwei Huang Published: 2026-03-11 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.10291v1 The remarkable progress of vision-language models (VLMs) has enabled GUI agents to interact with computers in a human-like manner. Yet real-world computer-use tasks remain difficult due to long-horizon workflows, diverse interfaces, and frequent intermediate errors. Prior work equips agents with external memory built from large collections of trajectories, but relies on flat retrieval over discrete summaries or continuous embeddings, falling short of the structured organization and self-evolving characteristics of human memory. Inspired by the brain, we propose Hybrid Self-evolving Structured Memory (HyMEM), a graph-based memory that couples discrete high-level symbolic nodes with continuous trajectory embeddings. HyMEM maintains a graph structure to support multi-hop retrieval, self-evolution via node update operations, and on-the-fly working-memory refreshing during inference. Extensive experiments show that HyMEM consistently improves open-source GUI agents, enabling 7B/8B backbones to match or surpass strong closed-source models; notably, it boosts Qwen2.5-VL-7B by +22.5% and outperforms Gemini2.5-Pro-Vision and GPT-4o. --- ### Quantum entanglement provides a competitive advantage in adversarial games Authors: Peiyong Wang, Kieran Hymas, James Quach Published: 2026-03-11 Categories: quant-ph, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.10289v2 Whether uniquely quantum resources confer advantages in fully classical, competitive environments remains an open question. Competitive zero-sum reinforcement learning is particularly challenging, as success requires modelling dynamic interactions between opposing agents rather than static state-action mappings. Here, we conduct a controlled study isolating the role of quantum entanglement in a quantum-classical hybrid agent trained on Pong, a competitive Markov game. An 8-qubit parameterised quantum circuit serves as a feature extractor within a proximal policy optimisation framework, allowing direct comparison between separable circuits and architectures incorporating fixed (CZ) or trainable (IsingZZ) entangling gates. Entangled circuits consistently outperform separable counterparts with comparable parameter counts and, in low-capacity regimes, match or exceed classical multilayer perceptron baselines. Representation similarity analysis further shows that entangled circuits learn structurally distinct features, consistent with improved modelling of interacting state variables. These findings establish entanglement as a function resource for representation learning in competitive reinforcement learning. --- ### MultiwayPAM: Multiway Partitioning Around Medoids for LLM-as-a-Judge Score Analysis Authors: Chihiro Watanabe, Jingyu Sun Published: 2026-03-11 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.10287v2 LLM-as-a-Judge is a flexible framework for text evaluation, which allows us to obtain scores for the quality of a given text from various perspectives by changing the prompt template. Two main challenges in using LLM-as-a-Judge are computational cost of inference using a large language model (LLM), especially when evaluating a large number of instances, and inherent bias of an LLM evaluator. To address these issues and reveal the structure of score bias caused by an LLM evaluator, we propose to apply a tensor clustering method to a given LLM-as-a-Judge score tensor, whose entries are the scores for different combinations of questions, answerers, and evaluators. Specifically, we develop a new tensor clustering method MultiwayPAM, with which we can simultaneously estimate the cluster membership and the medoids for each mode of a given data tensor. By observing the medoids obtained by MultiwayPAM, we can gain knowledge about the membership of each question/answerer/evaluator cluster. We experimentally show the effectiveness of MultiwayPAM by applying it to the score tensors for two practical datasets. --- ### MultiwayPAM: Multiway Partitioning Around Medoids for LLM-as-a-Judge Score Analysis Authors: Chihiro Watanabe, Jingyu Sun Published: 2026-03-11 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.10287v1 LLM-as-a-Judge is a flexible framework for text evaluation, which allows us to obtain scores for the quality of a given text from various perspectives by changing the prompt template. Two main challenges in using LLM-as-a-Judge are computational cost of LLM inference, especially when evaluating a large number of texts, and inherent bias of an LLM evaluator. To address these issues and reveal the structure of score bias caused by an LLM evaluator, we propose to apply a tensor clustering method to a given LLM-as-a-Judge score tensor, whose entries are the scores for different combinations of questions, answerers, and evaluators. Specifically, we develop a new tensor clustering method MultiwayPAM, with which we can simultaneously estimate the cluster membership and the medoids for each mode of a given data tensor. By observing the medoids obtained by MultiwayPAM, we can gain knowledge about the membership of each question/answerer/evaluator cluster. We experimentally show the effectiveness of MultiwayPAM by applying it to the score tensors for two practical datasets. --- ### Conversational AI-Enhanced Exploration System to Query Large-Scale Digitised Collections of Natural History Museums Authors: Yiyuan Wang, Andrew Johnston, Zoë Sadokierski, Rhiannon Stephens, Shane T. Ahyong Published: 2026-03-11 Categories: cs.HC, cs.AI, cs.CY, cs.DL, cs.ET arXiv: https://arxiv.org/abs/2603.10285v1 Recent digitisation efforts in natural history museums have produced large volumes of collection data, yet their scale and scientific complexity often hinder public access and understanding. Conventional data management tools, such as databases, restrict exploration through keyword-based search or require specialised schema knowledge. This paper presents a system design that uses conversational AI to query nearly 1.7 million digitised specimen records from the life-science collections of the Australian Museum. Designed and developed through a human-centred design process, the system contains an interactive map for visual-spatial exploration and a natural-language conversational agent that retrieves detailed specimen data and answers collection-specific questions. The system leverages function-calling capabilities of contemporary large language models to dynamically retrieve structured data from external APIs, enabling fast, real-time interaction with extensive yet frequently updated datasets. Our work provides a new approach of connecting large museum collections with natural language-based queries and informs future designs of scientific AI agents for natural history museums. --- ### Copula-ResLogit: A Deep-Copula Framework for Unobserved Confounding Effects Authors: Kimia Kamal, Bilal Farooq Published: 2026-03-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.10284v1 A key challenge in travel demand analysis is the presence of unobserved factors that may generate non-causal dependencies, obscuring the true causal effects. To address the issue, the study introduces a novel deep learning based fully interpretable joint modelling framework, Copula-ResLogit, which integrates the flexibility of Residual Neural Network (ResNet) architectures with the dependence capturing capabilities of copula models. This hybrid structure enables us to first detect unobserved confounding through traditional copula function based joint modelling and then mitigate these hidden associations by incorporating deep learning components. The study applies this framework to two case studies, including the relationship between stress levels and wait time of pedestrians when crossing mid block in VR and the dependencies between travel mode choice and travel distance in London travel behaviour data. Results show that Copula-ResLogit substantially reduces or eliminates the dependencies, demonstrating the ability of residual layers to account for hidden confounding effects. --- ### Uncertainty, Vagueness, and Ambiguity in Human-Robot Interaction: Why Conceptualization Matters Authors: Xiaowen Sun, Cornelius Weber, Matthias Kerzel, Josua Spisak, Stefan Wermter Published: 2026-03-10 Categories: cs.HC, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2604.15339v1 Uncertainty, vagueness, and ambiguity are closely related and often confused concepts in human-robot interaction (HRI). In earlier studies, these concepts have been defined in contradictory ways and described using inconsistent terminology. This conceptual confusion and lack of terminological consistency undermine empirical comparability, thereby slowing the accumulation of theory. Consequently, consistent concepts that clarify these challenges, including their definitions, distinctions, and interrelationships, are needed in HRI. To address this lack of clarity, this paper proposes a consistent conceptual foundation for the challenges of uncertainty, vagueness, and ambiguity in HRI. First, we examine the meanings of these three terms in dictionaries. We then analyze the nature of their distinctions and interrelationships within the context of HRI. We further illustrate these characteristics through examples. Finally, we demonstrate how this consistent conceptual foundation facilitates the design of novel methods and the evaluation of existing methodologies for these phenomena. --- ### Facial-Expression-Aware Prompting for Empathetic LLM Tutoring Authors: Shuangquan Feng, Laura Fleig, Ruisen Tu, Philip Chi, Edmund Bu, Melinda Ozel, Junhua Ma, Teng Fei, Virginia R. de Sa Published: 2026-03-10 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2604.15336v2 Large language models (LLMs) enable increasingly capable tutoring-style conversational agents, yet effective tutoring requires sensitivity to learners' affective and cognitive states beyond text alone. Facial expressions provide immediate and practical cues of confusion, frustration, or engagement, but remain underexplored in LLM-driven tutoring. We investigate whether facial-expression-aware signals can improve empathetic tutoring responses through prompt-level integration, without end-to-end retraining. We build a scalable simulated tutoring environment where a student agent exhibits diverse facial behaviors from a large unlabeled human facial expression video dataset, and compare four tutor variants: a text-only LLM baseline, a multimodal baseline using a random facial frame, and two Action Unit estimation model (AUM)-based methods that either inject textual AU descriptions or select a peak-expression frame for visual grounding. Across 960 multi-turn conversations spanning three tutor backbones (GPT-5.1, Claude Opus 4.5, and Gemini 2.5 Pro), we evaluate targeted pairwise comparisons with five human raters and an exhaustive AI evaluator. AU-based conditioning consistently improves empathetic responsiveness to facial expressions across all tutor backbones, while AUM-guided peak-frame selection outperforms random-frame visual input. Textual AU abstraction and peak-frame visual injection show model-dependent advantages. Control analyses show that this improvement does not come at the expense of worse pedagogical clarity or responsiveness to textual cues. Overall, our results show that lightweight, structured facial expression representations can meaningfully enhance empathy in LLM-based tutoring systems with minimal overhead. Future work should evaluate these methods using real student facial data collected during authentic learning interactions. --- ### A Comparative Study on the Impact of Traditional Learning and Interactive Learning on Students' Academic Performance and Emotional Well-Being Authors: Siva Raja Sindiramutty Published: 2026-03-10 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2604.15335v1 The growing adoption of interactive learning tools in higher education offers new opportunities to enhance student performance and well-being. This study compares the effects of traditional and interactive learning methods on academic performance, engagement, motivation, and emotional well-being among 100 university students enrolled in a computer intrusion detection course. Participants were randomly assigned to either a traditional learning group (lectures and notes) or an interactive learning group utilising tools such as Kahoot, Panopto, Slido, Quizizz, Padlet, and educational videos. Academic achievement was measured through pre-tests, post-tests, final exams, and assignments, while engagement and emotional states were assessed using validated Likert-scale questionnaires. Results showed that students in the interactive group significantly outperformed their peers in both post-tests (67.48% vs. 53.36%) and final exams (80.8% vs. 61.44%). Interactive learners also demonstrated greater behavioural (+67.01%) and emotional engagement (+75.32%), along with enhanced emotional well-being marked by increased positive emotions (+66.67%) and reduced frustration. A significant drop in cognitive involvement (-39.8%) indicates possible cognitive overload. The pedagogical potential of interactive learning is reaffirmed by this result while reinforcing the need for balancing stimulation and cognitive level. Future research with larger, diverse samples is suggested for generalising and maximising outcomes. --- ### Beyond Passive Viewing: A Pilot Study of a Hybrid Learning Platform Augmenting Video Lectures with Conversational AI Authors: Mohammed Abraar, Raj Abhijit Dandekar, Rajat Dandekar, Sreedath Panat Published: 2026-03-10 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2604.15334v1 The exponential growth of AI education has brought millions of learners to online platforms, yet this massive scale has simultaneously exposed critical pedagogical shortcomings. Traditional video-based instruction, while cost-effective and scalable, demonstrates systematic failures in both sustaining learner engagement and facilitating the deep conceptual mastery essential for AI literacy. We present a pilot study evaluating a novel hybrid learning platform that integrates real-time conversational AI tutors with traditional video lectures. Our controlled experiment (N = 58, mean age M = 21.4, SD = 2.8) compared traditional video-based instruction with our AI-augmented video platform. This study employed a sequential within-subjects design where all participants first completed the traditional video condition followed by the AI-augmented condition, providing direct comparisons of learning outcomes. We measured learning effectiveness through immediate post-tests and delayed retention assessments (2-week delay). Results suggest improvements in learning performance: immediate post-test performance showed a large effect size (d = 1.505) with participants scoring 8.3 points higher after AI-augmented instruction (91.8 vs 83.5 out of 100, p < .001). Behavioral analytics revealed increased engagement duration (71.1% improvement with AI tutoring) in the experimental group. This pilot study provides preliminary evidence that conversational AI tutors may enhance traditional educational delivery, suggesting a potential avenue for developing scalable, adaptive learning systems. --- ### Evaluating Reliability Gaps in Large Language Model Safety via Repeated Prompt Sampling Authors: Keita Broadwater Published: 2026-03-10 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2604.09606v1 Traditional benchmarks for large language models (LLMs), such as HELM and AIR-BENCH, primarily assess safety risk through breadth-oriented evaluation across diverse tasks. However, real-world deployment often exposes a different class of risk: operational failures arising from repeated generations of the same prompt rather than broad task generalization. In high-stakes settings, response consistency and safety under repeated use are critical operational requirements. We introduce Accelerated Prompt Stress Testing (APST), a depth-oriented evaluation framework inspired by highly accelerated stress testing in reliability engineering. APST probes LLM behavior by repeatedly sampling identical prompts under controlled operational conditions, including temperature variation and prompt perturbation, to surface latent failure modes such as hallucinations, refusal inconsistency, and unsafe completions. Rather than treating failures as isolated events, APST characterizes them statistically as stochastic outcomes of repeated inference. We model observed safety failures using Bernoulli and binomial formulations to estimate per-inference failure probabilities, enabling quantitative comparison of operational risk across models and configurations. We apply APST to multiple instruction-tuned LLMs evaluated on AIR-BENCH 2024 derived safety and security prompts. While models exhibit similar performance under conventional single- or very-low-sample evaluation (N <= 3), repeated sampling reveals substantial variation in empirical failure probabilities across temperatures. These results demonstrate that shallow benchmark scores can obscure meaningful differences in reliability under sustained use. --- ### Human-AI Interaction Traces as Blackout Poetry: Reframing AI-Supported Writing as Found-Text Creativity Authors: Syemin Park, Soobin Park, Youn-kyung Lim Published: 2026-03-10 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2604.09605v1 LLMs offer new creative possibilities for writers but also raise concerns about authenticity and reader trust, particularly when AI involvement is disclosed. Prior research has largely framed this as an issue of transparency and provenance, emphasizing the disclosure of human-AI interaction traces that account for how much the AI wrote and what the human did. Yet such audit-oriented disclosures may risk reducing creative collaboration to quantification and surveillance. In this position paper, we argue for a different lens by exploring how human-AI interaction traces might instead function as expressive artifacts that foreground the meaning-making inherent in human-AI collaboration. Drawing inspiration from blackout poetry, we frame AI-generated text as found material through which writers' acts of curation and reinterpretation become inscribed atop the AI's original output. In this way, we suggest that designing interaction traces as aesthetic artifacts may help readers better appreciate and trust writers' creative contributions in AI-assisted writing. --- ### LLMs for Text-Based Exploration and Navigation Under Partial Observability Authors: Stephan Sandfuchs, Maximilian Melchert, Jörg Frochte Published: 2026-03-10 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.09604v1 Exploration and goal-directed navigation in unknown layouts are central to inspection, logistics, and search-and-rescue. We ask whether large language models (LLMs) can function as \emph{text-only} controllers under partial observability -- without code execution, tools, or program synthesis. We introduce a reproducible benchmark with oracle localisation in fixed ASCII gridworlds: each step reveals only a local $5\times5$ window around the agent and the model must select one of \texttt{UP/RIGHT/DOWN/LEFT}. Nine contemporary LLMs ranging from open/proprietary, dense / Mixture of Experts and instruction- vs. reasoning-tuned are evaluated on two tasks across three layouts of increasing difficulty: \emph{Exploration} (maximising revealed cells) and \emph{Navigation} (reach the goal on the shortest path). The experimental results are evaluated on quantitative metrics including \emph{success rate}, \emph{efficiency} such as normalised coverage and \emph{path length} vs. oracle as well as qualitative analysis. Reasoning-tuned models reliably complete navigation across all layouts, yet remain less efficient than oracle paths. Few-shot demonstrations in the prompt chiefly help these Reasoning-tuned models by reducing invalid moves and shortening paths, while classic dense instruction models remain inconsistent. We observe characteristic action priors (UP/RIGHT) that can induce looping under partial observability. Overall, training regimen and test-time deliberation predict control ability better than raw parameter count. These findings suggest lightweight hybridisation with classical online planners as a practical route to deployable partial map systems. --- ### ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarios Authors: Xinyi Hu, Yuhao Shen, Baolin Zhang, Hengxin Zhang, Jun Dai, Shuang Ge, Lei Chen, Yue Li, Mingcheng Wan Published: 2026-03-10 Categories: cs.DC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.09603v2 Speculative Decoding promises to accelerate the inference of Large Language Models, yet its efficacy often degrades in production-grade serving. Existing evaluations typically overlook the compute-bound nature of high-concurrency regimes, where verification compute becomes the dominant bottleneck. Consequently, prior methods face a dilemma: static trees incur massive verification waste, while dynamic trees suffer from cumulative misjudgments and kernel incompatibility. To bridge this gap, we introduce ECHO, a high concurrency-oriented framework integrated into SGLang that reformulates speculative execution as a budgeted scheduling problem. Crucially, ECHO employs sparse confidence gating to manage the batch as a unified super-tree, elastically pivoting budget between depth and width to co-optimize the trade-off between reducing global verification steps and maximizing per-step efficiency. Extensive evaluations across diverse model scales-particularly the industrial-grade Qwen3-235B-demonstrate that ECHO consistently outperforms SOTA methods in both low-load and high-load scenarios, achieving up to 5.35x walltime speedup and delivering over 20% relative speedup gain. --- ### From Scalars to Tensors: Declared Losses Recover Epistemic Distinctions That Neutrosophic Scalars Cannot Express Authors: Tony Mason Published: 2026-03-10 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2604.09602v1 Leyva-Vázquez and Smarandache (2025) demonstrated that neutrosophic T/I/F evaluation, where Truth, Indeterminacy, and Falsity are independent dimensions not constrained to sum to 1.0, which reveals "hyper-truth"' (T+I+F > 1.0) in 35% of complex epistemic cases evaluated by LLMs. We extend their work in two directions. First, we replicate and extend their experiment across five model families from five vendors (Anthropic, Meta, DeepSeek, Alibaba, Mistral), finding hyper-truth in 84% of unconstrained evaluations, which confirms the phenomenon is cross-vendor under our prompt protocol. Second, and more significantly, we identify a limitation of scalar T/I/F that their framework cannot address: models adopting an `"Absorption" position (T=0, I=1, F=0) produce identical scalar outputs for fundamentally different epistemic situations (paradox, ignorance, contingency), collapsing the very distinctions neutrosophic logic was designed to preserve. We demonstrate that extending the evaluation to include declared losses (structured descriptions of what the model cannot evaluate and why) substantially recovers these distinctions. Models producing identical scalars for paradox and ignorance produce nearly disjoint loss vocabularies (Jaccard similarity < 0.10 on loss description keywords), with domain-specific, severity-rated loss declarations that differentiate the nature of their uncertainty. This suggests that scalar T/I/F is a necessary but insufficient representation of epistemic state, and that tensor-structured output (scalars + losses) provides a more faithful model of LLM epistemic capabilities. --- ### Automated Standardization of Legacy Biomedical Metadata Using an Ontology-Constrained LLM Agent Authors: Josef Hardi, Martin J. O'Connor, Marcos Martinez-Romero, Jean G. Rosario, Stephen A. Fisher, Mark A. Musen Published: 2026-03-10 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2604.08552v3 Descriptive scientific metadata in public repositories are often incomplete and inconsistent with community standards and ontologies, limiting data FAIRness. Large language models (LLMs) offer a promising approach to automatically standardizing such metadata when provided with relevant standards in machine-actionable form, such as metadata templates from the CEDAR Workbench. Prompt engineering, however, provides only fixed snapshots of these standards and relies on an LLM's pretrained knowledge to interpret and satisfy their constraints. We evaluate whether giving an LLM access to metadata specifications and authoritative terminology at runtime improves automated metadata standardization. Methods: We present ARMS, a tool-augmented LLM agent that retrieves complete CEDAR metadata templates and dynamically queries authoritative biomedical terminology services at execution time. We compared ARMS with a prompt-based approach on 839 legacy metadata records from the Human BioMolecular Atlas Program (HuBMAP), using expert-standardized records as the reference standard. Results: ARMS outperformed the prompt-based approach, increasing precision from 0.56 to 0.93 and recall from 0.51 to 0.85, with improvements across all field categories and assay types. The largest gains occurred for ontology-constrained fields, where precision increased from 0.36 to 0.92. Conclusion: LLMs cannot convert legacy metadata to standards-adherent form without knowledge of the relevant standards. ARMS improves metadata standardization by providing runtime access to authoritative resources that define valid metadata. Machine-actionable metadata standards enhance LLM-based rectification of legacy metadata, especially when they can be queried dynamically. --- ### Automated Standardization of Legacy Biomedical Metadata Using an Ontology-Constrained LLM Agent Authors: Josef Hardi, Martin J. O'Connor, Marcos Martinez-Romero, Jean G. Rosario, Stephen A. Fisher, Mark A. Musen Published: 2026-03-10 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2604.08552v2 Scientific metadata are often incomplete and noncompliant with community standards, limiting dataset findability, interoperability, and reuse. Even when standard metadata reporting guidelines exist, they typically lack machine-actionable representations. Producing FAIR datasets requires encoding metadata standards as machine-actionable templates with rich field specifications and precise value constraints. Recent work has shown that LLMs guided by field names and ontology constraints can improve metadata standardization, but these approaches treat constraints as static text prompts, relying on the model's training knowledge alone. We present an LLM-based metadata standardization system that queries standard reporting guidelines and authoritative biomedical terminology services in real time to retrieve canonically correct standards on demand. We evaluate this approach on 839 legacy metadata records from the Human BioMolecular Atlas Program (HuBMAP) using an expert-curated gold standard for exact-match assessment. Our evaluation shows that augmenting the LLM with real-time tool access consistently improves prediction accuracy over the LLM alone across both ontology-constrained and non-ontology-constrained fields, demonstrating a practical approach to automated standardization of biomedical metadata. --- ### Algebraic Structure Discovery for Real World Combinatorial Optimisation Problems: A General Framework from Abstract Algebra to Quotient Space Learning Authors: Min Sun, Federica Storti, Valentina Martino, Miguel Gonzalez-Andrades, Tony Kam-Thong Published: 2026-03-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.04941v1 Many combinatorial optimisation problems hide algebraic structures that, once exposed, shrink the search space and improve the chance of finding the global optimal solution. We present a general framework that (i) identifies algebraic structure, (ii) formalises operations, (iii) constructs quotient spaces that collapse redundant representations, and (iv) optimises directly over these reduced spaces. Across a broad family of rule-combination tasks (e.g., patient subgroup discovery and rule-based molecular screening), conjunctive rules form a monoid. Via a characteristic-vector encoding, we prove an isomorphism to the Boolean hypercube $\{0,1\}^n$ with bitwise OR, so logical AND in rules becomes bitwise OR in the encoding. This yields a principled quotient-space formulation that groups functionally equivalent rules and guides structure-aware search. On real clinical data and synthetic benchmarks, quotient-space-aware genetic algorithms recover the global optimum in 48% to 77% of runs versus 35% to 37% for standard approaches, while maintaining diversity across equivalence classes. These results show that exposing and exploiting algebraic structure offers a simple, general route to more efficient combinatorial optimisation. --- ### BLK-Assist: A Methodological Framework for Artist-Led Co-Creation with Generative AI Models Authors: Daniel Grimes, Rachel M. Harrison Published: 2026-03-10 Categories: cs.CY, cs.AI, cs.CV, cs.HC arXiv: https://arxiv.org/abs/2604.03249v1 This paper presents BLK-Assist, a modular framework for artist-specific fine-tuning of diffusion models using parameter-efficient methods. The system is implemented as a case study with a single professional artist's proprietary corpus and consists of three components: BLK-Conceptor (LoRA-adapted conceptual sketch generation), BLK-Stencil (LayerDiffuse-based transparency-preserving asset generation), and BLK-Upscale (hybrid Real-ESRGAN and texture-conditioned diffusion for high-resolution outputs). We document dataset composition, preprocessing, training configurations, and inference workflows to enable reproducibility with publicly available models to illustrate a privacy-preserving, consent-based approach to human-AI co-creation that maintains stylistic fidelity to the source corpus and can be adapted for other artists under similar constraints. --- ### Classifying Problem and Solution Framing in Congressional Social Media Authors: Misha Melnyk, Mitchell Dolny, Joshua D. Elkind, A. Michael Tjhin, Saisha Chebium, Blake VanBerlo, Annelise Russell, Michelle M. Buehlmann, Jesse Hoey Published: 2026-03-10 Categories: cs.CY, cs.AI, cs.CL, cs.SI arXiv: https://arxiv.org/abs/2604.03247v1 Policy setting in the USA according to the ``Garbage Can'' model differentiates between ``problem'' and ``solution'' focused processes. In this paper, we study a large dataset of US Senator postings on Twitter (1.68m tweets in total). Our objective is to develop an automated method to label Senatorial posts as either in the problem or solution streams. Two academic policy experts labeled a subset of 3967 tweets as either problem, solution, or other (anything not problem or solution). We split off a subset of 500 tweets into a test set, with the remaining 3467 used for training. During development, this training set was further split by 60/20/20 proportions for fitting, validation, and development test sets. We investigated supervised learning methods for building problem/solution classifiers directly on the training set, evaluating their performance in terms of F1 score on the validation set, allowing us to rapidly iterate through models and hyperparameters, achieving an average weighted F1 score of above 0.8 on cross validation across the three categories using a BERTweet Base model. --- ### Think Twice Before You Write -- an Entropy-based Decoding Strategy to Enhance LLM Reasoning Authors: Jiashu He, Meizhu Liu, Olaitan P Olaleye, Amit Agarwal, M. Avendi, Yassi Abbasi, Matthew Rowe, Hitesh Laxmichand Patel, Paul Li, Tao Sheng, Sujith Ravi, Dan Roth Published: 2026-03-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.00018v1 Decoding strategies play a central role in shaping the reasoning ability of large language models (LLMs). Traditional methods such as greedy decoding and beam search often suffer from error propagation, while sampling-based approaches introduce randomness without adequate robustness. Self-consistency improves reliability by aggregating multiple rollouts, but incurs significant computational overhead. We propose an entropy-guided decoding framework that introduces token-level adaptivity into generation. At each step, the model computes the entropy of the token distribution, identifies high-uncertainty positions, and selectively branches on these vulnerable points. A dynamic pool of partial rollouts is maintained and expanded until solutions are completed, concentrating computation where uncertainty is greatest and avoiding unnecessary exploration in confident regions. To enable efficient termination, we apply a rollout-level Entropy After </Think> (EAT) stopping criterion by performing entropy evaluation after the full reasoning trace, rather than incrementally at every step. Experiments on GSM8K, AMC2023, and their perturbed variants demonstrate that our method achieves consistently strong accuracy. Notably, on smaller LLMs, performance is comparable to GPT-5 while operating at a fraction of the cost. --- ### Semantic Shifts of Psychological Concepts in Scientific and Popular Media Discourse: A Distributional Semantics Analysis of Russian-Language Corpora Authors: Orlova Anastasia Published: 2026-03-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.00017v1 This article examines semantic shifts in psychological concepts across scientific and popular media discourse using methods of distributional semantics applied to Russian-language corpora. Two corpora were compiled: a scientific corpus of approximately 300 research articles from the journals Psychology. Journal of the Higher School of Economics and Vestnik of Saint Petersburg University. Psychology (767,543 tokens) and a popular science corpus consisting of texts from the online psychology platforms Yasno and Chistye kogntsii (1,199,150 tokens). After preprocessing (OCR recognition, lemmatization, removal of stop words and non-informative characters), the corpora were analyzed through frequency analysis, clustering, and the identification of semantic associations. The results reveal significant differences in vocabulary and conceptual framing between the two discourse types: scientific texts emphasize methodological and clinical terminology, while popular science materials foreground everyday experience and therapeutic practice. A comparison of semantic associations for key concepts such as burnout and depression shows that scientific discourse links these terms to psychological resources, symptomatology, and diagnostic constructs, whereas popular science discourse frames them through personal narratives, emotions, and everyday situations. These findings demonstrate a clear shift from precise professional terminology toward more generalized and experiential meanings in popular media discourse and confirm the effectiveness of distributional semantics methods for identifying semantic transformations of psychological concepts across different communicative contexts. --- ### Are they human? Detecting large language models by probing human memory constraints Authors: Simon Schug, Brenden M. Lake Published: 2026-03-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.00016v1 The validity of online behavioral research relies on study participants being human rather than machine. In the past, it was possible to detect machines by posing simple challenges that were easily solved by humans but not by machines. General-purpose agents based on large language models (LLMs) can now solve many of these challenges, threatening the validity of online behavioral research. Here we explore the idea of detecting humanness by using tasks that machines can solve too well to be human. Specifically, we probe for the existence of an established human cognitive constraint: limited working memory capacity. We show that cognitive modeling on a standard serial recall task can be used to distinguish online participants from LLMs even when the latter are specifically instructed to mimic human working memory constraints. Our results demonstrate that it is viable to use well-established cognitive phenomena to distinguish LLMs from humans. --- ### ASCAT: An Arabic Scientific Corpus and Benchmark for Advanced Translation Evaluation Authors: Serry Sibaee, Khloud Al Jallad, Zineb Yousfi, Israa Elsayed Elhosiny, Yousra El-Ghawi, Batool Balah, Omer Nacar Published: 2026-03-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.00015v1 We present ASCAT (Arabic Scientific Corpus for Advanced Translation), a high-quality English-Arabic parallel benchmark corpus designed for scientific translation evaluation constructed through a systematic multi-engine translation and human validation pipeline. Unlike existing Arabic-English corpora that rely on short sentences or single-domain text, ASCAT targets full scientific abstracts averaging 141.7 words (English) and 111.78 words (Arabic), drawn from five scientific domains: physics, mathematics, computer science, quantum mechanics, and artificial intelligence. Each abstract was translated using three complementary architectures generative AI (Gemini), transformer-based models (Hugging Face \texttt{quickmt-en-ar}), and commercial MT APIs (Google Translate, DeepL) and subsequently validated by domain experts at the lexical, syntactic, and semantic levels. The resulting corpus contains 67,293 English tokens and 60,026 Arabic tokens, with an Arabic vocabulary of 17,604 unique words reflecting the morphological richness of the language. We benchmark three state-of-the-art LLMs on the corpus GPT-4o-mini (BLEU: 37.07), Gemini-3.0-Flash-Preview (BLEU: 30.44), and Qwen3-235B-A22B (BLEU: 23.68) demonstrating its discriminative power as an evaluation benchmark. ASCAT addresses a critical gap in scientific MT resources for Arabic and is designed to support rigorous evaluation of scientific translation quality and training of domain-specific translation models. --- ### Disentangling Prompt Element Level Risk Factors for Hallucinations and Omissions in Mental Health LLM Responses Authors: Congning Ni, Sarvech Qadir, Bryan Steitz, Mihir Sachin Vaidya, Qingyuan Song, Lantian Xia, Shelagh Mulvaney, Siru Liu, Hyeyoung Ryu, Leah Hecht, Amy Bucher, Christopher Symons et al. Published: 2026-03-10 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2604.00014v1 Mental health concerns are often expressed outside clinical settings, including in high-distress help seeking, where safety-critical guidance may be needed. Consumer health informatics systems increasingly incorporate large language models (LLMs) for mental health question answering, yet many evaluations underrepresent narrative, high-distress inquiries. We introduce UTCO (User, Topic, Context, Tone), a prompt construction framework that represents an inquiry as four controllable elements for systematic stress testing. Using 2,075 UTCO-generated prompts, we evaluated Llama 3.3 and annotated hallucinations (fabricated or incorrect clinical content) and omissions (missing clinically necessary or safety-critical guidance). Hallucinations occurred in 6.5% of responses and omissions in 13.2%, with omissions concentrated in crisis and suicidal ideation prompts. Across regression, element-specific matching, and similarity-matched comparisons, failures were most consistently associated with context and tone, while user-background indicators showed no systematic differences after balancing. These findings support evaluating omissions as a primary safety outcome and moving beyond static benchmark question sets. --- ### C2F-Thinker: Coarse-to-Fine Reasoning with Hint-Guided Reinforcement Learning for Multimodal Sentiment Analysis Authors: Miaosen Luo, Zhenhao Yang, Jieshen Long, Jinghu Sun, Yichu Liu, Sijie Mai Published: 2026-03-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.00013v2 Multimodal sentiment analysis aims to integrate textual, acoustic, and visual information for deep emotional understanding. Despite the progress of multimodal large language models (MLLMs) via supervised fine-tuning, their "black-box" nature hinders interpretability. While Chain-of-Thought (CoT) reasoning offers a potential remedy, it is constrained by high manual annotation costs and the inherent challenges of reinforcement learning (RL), such as reward sparsity and low exploration efficiency on hard samples. This paper presents C2F-Thinker, a framework that harmonizes coarse-to-fine structured reasoning with hint-guided RL through a two-stage progressive training pipeline. In the first stage, we conduct cold-start supervised fine-tuning using high-quality CoT data distilled from a larger teacher model, consisting of three distinct phases: polarity judgment, intermediate analysis, and fine-grained scoring. This equips the base model with a structured emotional reasoning paradigm. In the second stage, we introduce a hint-guided Group Relative Policy Optimization (GRPO) algorithm. By injecting correct initial polarity predictions as hints during the sampling process, the model is guided toward accurate reasoning paths, effectively mitigating cascading errors and enhancing the utilization of hard samples. Furthermore, a multi-faceted reward function incorporating classification, regression, and formatting constraints is designed to refine prediction accuracy while preserving interpretability. Experimental results demonstrate that C2F-Thinker achieves competitive performance on fine-grained sentiment regression tasks while significantly outperforming baselines in cross-domain generalization. This highlights its potential in building trustworthy and robust sentiment analysis systems for real-world applications. --- ### Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms Authors: Mingjie Li, Wai Man Si, Michael Backes, Yang Zhang, Yisen Wang Published: 2026-03-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.00012v1 Despite the impressive performance of general-purpose large language models (LLMs), they often require fine-tuning or post-training to excel at specific tasks. For instance, large reasoning models (LRMs), such as the DeepSeek-R1 series, demonstrate strong reasoning capabilities after post-training different general large language models on diverse chain-of-thought (CoT) datasets. However, this additional training frequently comes at the cost of reduced safety, as the fine-tuned or post-trained models tend to exhibit more harmful behaviors compared with the regular LLMs before post-training or fine-tuning, potentially leading to harmful outcomes due to their enhanced capabilities. Taking LRMs as an example, we first investigate the underlying cause of this safety degradation in this paper. Our analysis reveals that post-training can mask the original safety mechanisms of the base LLM, while over-amplifying representations related to their post-training ability. But luckily, we also find that LRMs' safety mechanisms still exist instead of being removed during their post-training. Based on these findings, we propose a lightweight and cost-effective solution called SafeReAct that restores the suppressed safety behaviors by aligning with LoRA adapters on a few layers. Experiments on four state-of-the-art LRMs show that our method significantly improves safety on harmful prompts without compromising reasoning performance. Besides LRMs, additional results on other domain-specific LLMs, like medical models, further confirm the generality and effectiveness of our approach. --- ### Quantifying Gender Bias in Large Language Models: When ChatGPT Becomes a Hiring Manager Authors: Nina Gerszberg, Janka Hamori, Andrew Lo Published: 2026-03-10 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2604.00011v1 The growing prominence of large language models (LLMs) in daily life has heightened concerns that LLMs exhibit many of the same gender-related biases as their creators. In the context of hiring decisions, we quantify the degree to which LLMs perpetuate societal biases and investigate prompt engineering as a bias mitigation technique. Our findings suggest that for a given resumé, an LLM is more likely to hire a female candidate and perceive them as more qualified, but still recommends lower pay relative to male candidates. --- ### Interview-Informed Generative Agents for Product Discovery: A Validation Study Authors: Zichao Wang, Alexa Siu Published: 2026-03-10 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2603.29890v1 Large language models (LLMs) have shown strong performance on standardized social science instruments, but their value for product discovery remains unclear. We investigate whether interview-informed generative agents can simulate user responses in concept testing scenarios. Using in-depth workflow interviews with knowledge workers, we created personalized agents and compared their evaluations of novel AI concepts against the same participants' responses. Our results show that agents are distribution-calibrated but identity-imprecise: they fail to replicate the specific individual they are grounded in, yet approximate population-level response distributions. These findings highlight both the potential and the limits of LLM simulation in design research. While unsuitable as a substitute for individual-level insights, simulation may provide value for early-stage concept screening and iteration, where distributional accuracy suffices. We discuss implications for integrating simulation responsibly into product development workflows. --- ### LITTA: Late-Interaction and Test-Time Alignment for Visually-Grounded Multimodal Retrieval Authors: Seonok Kim Published: 2026-03-10 Categories: cs.IR, cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2603.26683v1 Retrieving relevant evidence from visually rich documents such as textbooks, technical reports, and manuals is challenging due to long context, complex layouts, and weak lexical overlap between user questions and supporting pages. We propose LITTA, a query-expansion-centric retrieval framework for evidence page retrieval that improves multimodal document retrieval without retriever retraining. Given a user query, LITTA generates complementary query variants using a large language model and retrieves candidate pages for each variant using a frozen vision retriever with late-interaction scoring. Candidates from expanded queries are then aggregated through reciprocal rank fusion to improve evidence coverage and reduce sensitivity to any single phrasing. This simple test-time strategy significantly improves retrieval robustness while remaining compatible with existing multimodal embedding indices. We evaluate LITTA on visually grounded document retrieval tasks across three domains: computer science, pharmaceuticals, and industrial manuals. Multi-query retrieval consistently improves top-k accuracy, recall, and MRR compared to single-query retrieval, with particularly large gains in domains with high visual and semantic variability. Moreover, the accuracy-efficiency trade-off is directly controllable by the number of query variants, making LITTA practical for deployment under latency constraints. These results demonstrate that query expansion provides a simple yet effective mechanism for improving visually grounded multimodal retrieval. --- ### Operationalizing Perceptions of Agent Gender: Foundations and Guidelines Authors: Katie Seaborn, Madeleine Steeds, Ilaria Torre, Martina De Cet, Katie Winkle, Marcus Göransson Published: 2026-03-10 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2603.26682v1 The "gender" of intelligent agents, virtual characters, social robots, and other agentic machines has emerged as a fundamental topic in studies of people's interactions with computers. Perceptions of agent gender can help explain user attitudes and behaviours -- from preferences to toxicity to stereotyping -- across a variety of systems and contexts of use. Yet, standards in capturing perceptions of agent gender do not exist. A scoping review was conducted to clarify how agent gender has been operationalized -- labelled, defined, and measured -- as a perceptual variable. One-third of studies manipulated but did not measure agent gender. Norms in operationalizations remain obscure, limiting comprehension of results, congruity in measurement, and comparability for meta-analyses. The dominance of the gender binary model and latent anthropocentrism have placed arbitrary limits on knowledge generation and reified the status quo. We contribute a systematically-developed and theory-driven meta-level framework that offers operational clarity and practical guidance for greater rigour and inclusivity. --- ### Developing Machine Learning-Based Watch-to-Warning Severe Weather Guidance from the Warn-on-Forecast System Authors: Montgomery Flora, Samuel Varga, Corey Potvin, Noah Lang Published: 2026-03-10 Categories: physics.ao-ph, cs.AI, cs.LG, physics.data-an arXiv: https://arxiv.org/abs/2603.20250v1 While machine learning (ML) post-processing of convection-allowing model (CAM) output for severe weather hazards (large hail, damaging winds, and/or tornadoes) has shown promise for very short lead times (0-3 hours), its application to slightly longer forecast windows remains relatively underexplored. In this study, we develop and evaluate a grid-based ML framework to predict the probability of severe weather hazards over the next 2-6 hours using forecast output from the Warn-on-Forecast System (WoFS). Our dataset includes WoFS ensemble forecasts valid every 5 minutes out to 6 hours from 108 days during the 2019--2023 NOAA Hazardous Weather Testbed Spring Forecasting Experiments. We train ML models to generate probabilistic forecasts of severe weather akin to Storm Prediction Center outlooks (i.e., likelihood of a tornado, severe wind, or severe hail event within 36 km of each point). We compare a histogram gradient-boosted tree (HGBT) model and a deep learning U-Net approach against a carefully calibrated baseline generated from 2-5 km updraft helicity. Results indicate that the HGBT and U-Net outperform the baseline, particularly at higher probability thresholds. The HGBT achieves the best performance metrics, but predicted probabilities cap at 60% while the U-net forecasts extend to 100%. Similar to previous studies, the U-Net produces spatially smoother guidance than the tree-based method. These findings add to the growing evidence of the effectiveness of ML-based CAM post-processing for providing short-term severe weather guidance. --- ### Stability of AI Governance Systems: A Coupled Dynamics Model of Public Trust and Social Disruptions Authors: Jiaqi Lai, Hou Liang, Weihong Huang Published: 2026-03-10 Categories: cs.CY, cs.AI, cs.HC, cs.MA arXiv: https://arxiv.org/abs/2603.20248v2 AI systems are increasingly entrenched in public governance, yet scholarship lacks formal tools to determine when deviations of public trust in algorithmic institutions dissipate and when they grow into collapse. Stability refers here to asymptotic recovery from finite state perturbations under fixed structural parameters. We address this gap by developing a mathematical framework for institutional trust stability that couples a Friedkin-Johnsen opinion dynamics process with a Hawkes-inspired intensity process for AI controversies. Motivated by the Computers-Are-Social-Actors literature and recent studies of trust in large language models, this bidirectional coupling reveals that governance stability depends on the structural architecture of the information environment rather than absolute trust levels. We derive an exact spectral stability criterion delineating resilience from collapse, demonstrating how event self-excitation and memory persistence systematically narrow the stable parameter regime. Our structural analysis yields four counterintuitive structural implications: high-trust systems can be structurally fragile, low-trust environments can be structurally stable, dynamical stability neither measures nor guarantees algorithmic fairness or legitimacy, and network topology reshapes equilibrium heterogeneity while its effect on spectral stability is uniformly bounded in an explicit memory-dominated regime. Governance assessment should therefore pair normative evaluation of harms and fairness with structural analysis of recoverability, rather than treating either as a proxy for the other. --- ### Decoding the decoder: Contextual sequence-to-sequence modeling for intracortical speech decoding Authors: Michal Olak, Tommaso Boccato, Matteo Ferrante Published: 2026-03-10 Categories: cs.CL, cs.AI, cs.NE, q-bio.NC arXiv: https://arxiv.org/abs/2603.20246v1 Speech brain--computer interfaces require decoders that translate intracortical activity into linguistic output while remaining robust to limited data and day-to-day variability. While prior high-performing systems have largely relied on framewise phoneme decoding combined with downstream language models, it remains unclear what contextual sequence-to-sequence decoding contributes to sublexical neural readout, robustness, and interpretability. We evaluated a multitask Transformer-based sequence-to-sequence model for attempted speech decoding from area 6v intracortical recordings. The model jointly predicts phoneme sequences, word sequences, and auxiliary acoustic features. To address day-to-day nonstationarity, we introduced the Neural Hammer Scalpel (NHS) calibration module, which combines global alignment with feature-wise modulation. We further analyzed held-out-day generalization and attention patterns in the encoder and decoders. On the Willett et al. dataset, the proposed model achieved a state-of-the-art phoneme error rate of 14.3%. Word decoding reached 25.6% WER with direct decoding and 19.4% WER with candidate generation and rescoring. NHS substantially improved both phoneme and word decoding relative to linear or no day-specific transform, while held-out-day experiments showed increasing degradation on unseen days with temporal distance. Attention visualizations revealed recurring temporal chunking in encoder representations and distinct use of these segments by phoneme and word decoders. These results indicate that contextual sequence-to-sequence modeling can improve the fidelity of neural-to-phoneme readout from intracortical speech signals and suggest that attention-based analyses can generate useful hypotheses about how neural speech evidence is segmented and accumulated over time. --- ### Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data Authors: Hyunji Nam, Haoran Li, Natasha Jaques Published: 2026-03-10 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.19294v6 While post-training has successfully improved large language models (LLMs) across a variety of domains, these gains heavily rely on human-labeled data or external verifiers. Existing data has already been exploited, and new data is expensive to collect. Moreover, true intelligence goes far beyond verifiable tasks. Therefore, we need self-improvement frameworks that are less dependent on external signals and more broadly applicable to both verifiable and non-verifiable domains. We propose **Mutual Information Preference Optimization (MIPO)**, a contrastive data augmentation method that constructs preference pairs by generating a positive response conditioning on the correct prompt, and a negative response by conditioning on a random, unrelated prompt. We show that using Direct Preference Optimization to learn from this paired data maximizes pointwise mutual information *under the base LLM* between prompts and model responses. Experiments with with 1-7B parameter Llama and Qwen instruct models show that MIPO achieves 3-16% gains (and 51% increase for Qwen2.5-1.5B-Instruct) on personalization compared to prompting baselines. Surprisingly, MIPO can also be useful in verifiable domains, such as math and multiple-choice question answering, yielding 1-20% gains *without any additional data or external supervision*. These results suggest a promising direction for self-improvement using intrinsic signals derived from contrastive data pairs. --- ### Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data Authors: Hyunji Nam, Haoran Li, Natasha Jaques Published: 2026-03-10 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.19294v5 While post-training has successfully improved large language models (LLMs) across a variety of domains, these gains heavily rely on human-labeled data or external verifiers. Existing data has already been exploited, and new data is expensive to collect. Moreover, true intelligence goes far beyond verifiable tasks. Therefore, we need self-improvement frameworks that are less dependent on external signals and more broadly applicable to both verifiable and non-verifiable domains. We propose **Mutual Information Preference Optimization (MIPO)**, a contrastive data augmentation method that constructs preference pairs by generating a positive response conditioning on the correct prompt, and a negative response by conditioning on a random, unrelated prompt. We show that using Direct Preference Optimization to learn from this paired data maximizes pointwise mutual information *under the base LLM* between prompts and model responses. Experiments with with 1-7B parameter Llama and Qwen instruct models show that MIPO achieves 3-16% gains (and 51% increase for Qwen2.5-1.5B-Instruct) on personalization compared to prompting baselines. Surprisingly, MIPO can also be useful in verifiable domains, such as math and multiple-choice question answering, yielding 1-20% gains *without any additional data or external supervision*. These results suggest a promising direction for self-improvement using intrinsic signals derived from contrastive data pairs. --- ### LLM-MRD: LLM-Guided Multi-View Reasoning Distillation for Fake News Detection Authors: Weilin Zhou, Shanwen Tan, Enhao Gu, Yurong Qian Published: 2026-03-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.19293v1 Multimodal fake news detection is crucial for mitigating societal disinformation. Existing approaches attempt to address this by fusing multimodal features or leveraging Large Language Models (LLMs) for advanced reasoning. However, these methods suffer from serious limitations, including a lack of comprehensive multi-view judgment and fusion, and prohibitive reasoning inefficiency due to the high computational costs of LLMs. To address these issues, we propose \textbf{LLM}-Guided \textbf{M}ulti-View \textbf{R}easoning \textbf{D}istillation for Fake News Detection ( \textbf{LLM-MRD}), a novel teacher-student framework. The Student Multi-view Reasoning module first constructs a comprehensive foundation from textual, visual, and cross-modal perspectives. Then, the Teacher Multi-view Reasoning module generates deep reasoning chains as rich supervision signals. Our core Calibration Distillation mechanism efficiently distills this complex reasoning-derived knowledge into the efficient student model. Experiments show LLM-MRD significantly outperforms state-of-the-art baselines. Notably, it demonstrates a comprehensive average improvement of 5.19\% in ACC and 6.33\% in F1-Fake when evaluated across all competing methods and datasets. Our code is available at https://github.com/Nasuro55/LLM-MRD --- ### Automatic Analysis of Collaboration Through Human Conversational Data Resources: A Review Authors: Yi Yu, Maria Boritchev, Chloé Clavel Published: 2026-03-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.19292v3 Collaboration is a task-oriented, high-level human behavior. In most cases, conversation serves as the primary medium for information exchange and coordination, making conversational data a valuable resource for the automatic analysis of collaborative processes. In this paper, we focus on verbal aspects of collaboration and conduct a review of collaboration analysis using task-oriented conversation resources, encompassing related theories, coding schemes, tasks, and modeling approaches. We aim to address the question of how to utilize task-oriented human-human conversational data for collaboration analysis. We hope our review will serve as a practical resource and illuminate unexplored areas for future collaboration analysis. --- ### A Visualization for Comparative Analysis of Regression Models Authors: Nassime Mountasir, Baptiste Lafabregue, Bruno Albert, Nicolas Lachiche Published: 2026-03-10 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2603.19291v1 As regression is a widely studied problem, many methods have been proposed to solve it, each of them often requiring setting different hyper-parameters. Therefore, selecting the proper method for a given application may be very difficult and relies on comparing their performances. Performance is usually measured using various metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), or R-squared (R${}^2$). These metrics provide a numerical summary of predictive accuracy by quantifying the difference between predicted and actual values. However, while these metrics are widely used in the literature for summarizing model performance and useful to distinguish between models performing poorly and well, they often aggregate too much information. This article addresses these limitations by introducing a novel visualization approach that highlights key aspects of regression model performance. The proposed method builds upon three main contributions: (1) considering the residuals in a 2D space, which allows for simultaneous evaluation of errors from two models, (2) leveraging the Mahalanobis distance to account for correlations and differences in scale within the data, and (3) employing a colormap to visualize the percentile-based distribution of errors, making it easier to identify dense regions and outliers. By graphically representing the distribution of errors and their correlations, this approach provides a more detailed and comprehensive view of model performance, enabling users to uncover patterns that traditional aggregate metrics may obscure. The proposed visualization method facilitates a deeper understanding of regression model performance differences and error distributions, enhancing the evaluation and comparison process. --- ### Semantic Chameleon: Corpus-Dependent Poisoning Attacks and Defenses in RAG Systems Authors: Scott Thornton Published: 2026-03-10 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.18034v1 Retrieval-Augmented Generation (RAG) systems extend large language models (LLMs) with external knowledge sources but introduce new attack surfaces through the retrieval pipeline. In particular, adversaries can poison retrieval corpora so that malicious documents are preferentially retrieved at inference time, enabling targeted manipulation of model outputs. We study gradient-guided corpus poisoning attacks against modern RAG pipelines and evaluate retrieval-layer defenses that require no modification to the underlying LLM. We implement dual-document poisoning attacks consisting of a sleeper document and a trigger document optimized using Greedy Coordinate Gradient (GCG). In a large-scale evaluation on the Security Stack Exchange corpus (67,941 documents) with 50 attack attempts, gradient-guided poisoning achieves a 38.0 percent co-retrieval rate under pure vector retrieval. We show that a simple architectural modification, hybrid retrieval combining BM25 and vector similarity, substantially mitigates this attack. Across all 50 attacks, hybrid retrieval reduces gradient-guided attack success from 38 percent to 0 percent without modifying the model or retraining the retriever. When attackers jointly optimize payloads for both sparse and dense retrieval signals, hybrid retrieval can be partially circumvented, achieving 20-44 percent success, but still significantly raises attack difficulty relative to vector-only retrieval. Evaluation across five LLM families (GPT-5.3, GPT-4o, Claude Sonnet 4.6, Llama 4, and GPT-4o-mini) shows attack success ranging from 46.7 percent to 93.3 percent. Cross-corpus evaluation on the FEVER Wikipedia dataset (25 attacks) yields 0 percent attack success across all retrieval configurations. --- ### Privacy and Safety Experiences and Concerns of U.S. Women Using Generative AI for Seeking Sexual and Reproductive Health Information Authors: Ina Kaleva, Xiao Zhan, Ruba Abu-Salma, Jose Such Published: 2026-03-10 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2603.16918v1 The rapid adoption of generative AI (GenAI) chatbots has reshaped access to sexual and reproductive health (SRH) information, particularly following the overturning of Roe v. Wade, as individuals assigned female at birth increasingly turn to online sources. However, existing research remains largely model-centered, paying limited attention to user privacy and safety. We conducted semi-structured interviews with 18 U.S.-based participants from both restrictive and non-restrictive states who had used GenAI chatbots to seek SRH information. Adoption was influenced by perceived utility, usability, credibility, accessibility, and anthropomorphism, and many participants disclosed sensitive personal SRH details. Participants identified multiple privacy risks, including excessive data collection, government surveillance, profiling, model training, and data commodification. While most participants accepted these risks in exchange for perceived utility, abortion-related queries elicited heightened safety concerns. Few participants employed protective strategies beyond minimizing disclosures or deleting data. Based on these findings, we offer design and policy recommendations, such as health-specific features and stronger moderation practices, to enhance privacy and safety in GenAI-supported SRH information seeking. --- ### HoloByte: Continuous Hyperspherical Distillation for Tokenizer-Free Modeling Authors: Vladimer Khasia Published: 2026-03-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.16917v1 Sequence modeling universally relies on discrete subword tokenization to circumvent the $\mathcal{O}(N^2)$ computational intractability of native byte-level attention. However, this heuristic quantization imposes artificial morphological boundaries, enforces vocabulary dependence, and fractures the continuity of the optimization landscape. To resolve this dichotomy, we introduce \textbf{HoloByte}: a strictly tokenizer-free framework utilizing Continuous Hyperspherical Distillation. HoloByte partitions discrete byte sequences into fixed-capacity chunks and projects them into a continuous, strictly bounded hyperspherical manifold via an invertible, dimension-preserving orthogonal rotation operator. This spatial superposition allows a macroscopic transformer to operate exclusively on compressed continuous representations, formally reducing the exact attention time complexity from $\mathcal{O}(N^2D)$ to $\mathcal{O}\left( \frac{N^2}{W^2}D + ND^2 \right)$. A localized causal micro-decoder subsequently unbinds these representations to compute exact byte-level distributions. To govern this continuous trajectory, we propose a dual-objective formulation incorporating a mathematically precise Holographic Latent Mean Squared Error, which strictly bounds the gradient and guarantees asymptotic stability. Theoretically, we derive the minimal embedding dimension $D = Ω(W \ln |\mathcal{V}|)$ required to ensure error-free discrete recovery from the continuous manifold. Empirically, under strictly matched parameter constraints, HoloByte is systematically outperforming a comparable discrete Byte-Pair Encoding (BPE) baseline. These results establish Continuous Hyperspherical Distillation as a mathematically rigorous and computationally tractable foundation for vocabulary-invariant sequence modeling. The code is available at https://github.com/VladimerKhasia/HoloByte --- ### Quantizer-Aware Hierarchical Neural Codec Modeling for Speech Deepfake Detection Authors: Jinyang Wu, Zihan Pan, Qiquan Zhang, Sailor Hardik Bhupendra, Soumik Mondal Published: 2026-03-10 Categories: cs.SD, cs.AI, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2603.16914v1 Neural audio codecs discretize speech via residual vector quantization (RVQ), forming a coarse-to-fine hierarchy across quantizers. While codec models have been explored for representation learning, their discrete structure remains underutilized in speech deepfake detection. In particular, different quantization levels capture complementary acoustic cues, where early quantizers encode coarse structure and later quantizers refine residual details that reveal synthesis artifacts. Existing systems either rely on continuous encoder features or ignore this quantizer-level hierarchy. We propose a hierarchy-aware representation learning framework that models quantizer-level contributions through learnable global weighting, enabling structured codec representations aligned with forensic cues. Keeping the speech encoder backbone frozen and updating only 4.4% additional parameters, our method achieves relative EER reductions of 46.2% on ASVspoof 2019 and 13.9% on ASVspoof5 over strong baselines. --- ### Quantum Amplitude Estimation for Catastrophe Insurance Tail-Risk Pricing: Empirical Convergence and NISQ Noise Analysis Authors: Alexis Kirke Published: 2026-03-10 Categories: stat.AP, cs.AI, cs.CE, stat.ML arXiv: https://arxiv.org/abs/2603.15664v1 Classical Monte Carlo methods for pricing catastrophe insurance tail risk converge at order reciprocal root N, requiring large simulation budgets to resolve upper-tail percentiles of the loss distribution. This sample-sparsity problem can lead to AI models trained on impoverished tail data, producing poorly calibrated risk estimates where insolvency risk is greatest. Quantum Amplitude Estimation (QAE), following Montanaro, achieves convergence approaching order reciprocal N in oracle queries - a quadratic speedup that, at scale, would enable high-resolution tail estimation within practical budgets. We validate this advantage empirically using a Qiskit Aer simulator with genuine Grover amplification. A complete pipeline encodes fitted lognormal catastrophe distributions into quantum oracles via amplitude encoding, producing small readout probabilities that enable safe Grover amplification with up to k=16 iterations. Seven experiments on synthetic and real (NOAA Storm Events, 58,028 records) data yield three main findings: an oracle-model advantage, that strong classical baselines win when analytical access is available, and that discretisation, not estimation, is the current bottleneck. --- ### OrthoAI v2: From Single-Agent Segmentation to Dual-Agent Treatment Planning for Clear Aligners Authors: Lansiaux Edouard, Leman Margaux Published: 2026-03-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.15663v1 We present OrthoAI v2, the second iteration of our open-source pipeline for AI-assisted orthodontic treatment planning with clear aligners, substantially extending the single-agent framework previously introduced. The first version established a proof-of-concept based on Dynamic Graph Convolutional Neural Networks (\dgcnn{}) for tooth segmentation but was limited to per-tooth centroid extraction, lacked landmark-level precision, and produced a scalar quality score without staging simulation. \vtwo{} addresses all three limitations through three principal contributions: (i)~a second agent adopting the Conditioned Heatmap Regression Methodology (\charm{})~\cite{rodriguez2025charm} for direct, segmentation-free dental landmark detection, fused with Agent~1 via a confidence-weighted orchestrator in three modes (parallel, sequential, single-agent); (ii)~a composite six-category biomechanical scoring model (biomechanics $\times$ 0.30 + staging $\times$ 0.20 + attachments $\times$ 0.15 + IPR $\times$ 0.10 + occlusion $\times$ 0.10 + predictability $\times$ 0.15) replacing the binary pass/fail check of v1; (iii)~a multi-frame treatment simulator generating $F = A \times r$ temporally coherent 6-DoF tooth trajectories via SLERP interpolation and evidence-based staging rules, enabling ClinCheck 4D visualisation. On a synthetic benchmark of 200 crowding scenarios, the parallel ensemble of OrthoAI v2 reaches a planning quality score of $92.8 \pm 4.1$ vs.\ $76.4 \pm 8.3$ for OrthoAI v1, a $+21\%$ relative gain, while maintaining full CPU deployability ($4.2 \pm 0.8$~s). ---