answer-correctness

Tag

Cards List
#answer-correctness

Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong

arXiv cs.CL · 2026-07-28 Cached

This paper studies behavioral detection of unfaithful chain-of-thought reasoning in LLMs, finding that answer correctness structures detection performance: on incorrect answers, where most unfaithfulness occurs, behavioral signals are at chance, while on correct answers they offer modest separation.

0 favorites 0 likes
#answer-correctness

Two Axes of LLM Abstention: Answer Correctness and Question Answerability

arXiv cs.CL · 2026-07-10 Cached

This paper investigates the two axes of LLM abstention: answer correctness and question answerability. It shows that a single confidence threshold conflates these two failure modes, and proposes a three-class selective acceptance framework with separate budgets. Experiments across five instruction-tuned models reveal that answerability is internally legible but poorly captured by output confidence or self-assessments.

0 favorites 0 likes
← Back to home

Submit Feedback