Tag
This paper introduces CASPO, a framework for aligning token-level confidence with step-wise logical correctness in large reasoning models using iterative Direct Preference Optimization. It also proposes Confidence-aware Thought (CaT) for dynamically pruning uncertain reasoning branches during inference to improve reliability and efficiency.
This study presents a 33-model atlas analyzing domain-level metacognitive monitoring in frontier LLMs using MMLU benchmarks, revealing significant variations in confidence calibration across different knowledge domains that are obscured by aggregate metrics.
This paper introduces a method for detecting hallucinations in large language models by leveraging the confidence of the first generated token, requiring only a single decode step.