cs.AIcs.PL

Ensemble Methodology for Reference-Free Confidence Estimation in LLM-based Code Summarization

📅 👥 8 authors arXiv:2611.09846v1

Authors

Abstract

This paper describes an approach and use case to estimate the correctness of LLM-generated COBOL summaries without access to human-authored references. The core intuition is that inter-model agreement on semantics is informative about truth, and that an LLM-as-judge can provide higher-fidelity pairwise assessments than traditional string- or embedding-based metrics. We operationalise this intuition with (i) controlled summary generation from diverse models; (ii) a LLM evaluator that compares pairs of summaries and emits structured judgments; and (iii) a calibrated aggregation rule that combines supportive evidence while penalising only corroborated contradictions.

Paper Information

arXiv ID:
2611.09846v1
Published:

Related Categories

cs.AIcs.PL