← 研踪 PaperTrailarXiv:2605.31561 · v2
What Am I Missing? Question-Answering as Hidden State Probing
首次提交 2026-05-30 01:27
版本更新 2026-11-17 03:48
雷达观测 2026-11-18 19:44
摘要
The study of test-time reasoning in large language models (LLMs) has attracted increasing interests due to its profound impact on many tasks, with early work tracing back to approaches such as chain-of-thought reasoning. The basic mechanism underlying the test-time reasoning process, however, is still under-studied: from the same input prompt, and even the same partial solution, LLMs can produce varied answers if sampled multiple times. In this paper, we leverage question-asking as an inference-time intervention that articulates information about the model's hidden state. Specifically, we present a student-teacher setting where a student asks questions to a teacher. We train a probe on the student's hidden state before and after asking a question and find it is predictive of the trajectory's final correctness, even before generating the teacher's answer. This suggests there is a meaningful signal from the self-diagnosis that occurs during question generation rather than information transfer from the teacher. We then frame question-asking as a sequential decision problem, using this probe as a quality score, and define a gating policy to ask questions that maximize likelihood of correctness. We find that the success of question-asking as an intervention is largely dependent on the model's self-consistency. Our empirical results show a gap between detection and recovery; while our gating policy captures model correctness and uncertainty, interventions are equally likely to harm correct trajectories as they are to recover incorrect ones. This gap between diagnosis and correction has broader implications on language models' capacity for self-refinement under uncertainty.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-17 03:48 · 最新观测版本
What Am I Missing? Question-Answering as Hidden State Probing
The study of test-time reasoning in large language models (LLMs) has attracted increasing interests due to its profound impact on many tasks, with early work tracing back to approaches such as chain-of-thought reasoning. The basic mechanism underlying the test-time reasoning process, however, is still under-studied: from the same input prompt, and even the same partial solution, LLMs can produce varied answers if sampled multiple times. In this paper, we leverage question-asking as an inference-time intervention that articulates information about the model's hidden state. Specifically, we present a student-teacher setting where a student asks questions to a teacher. We train a probe on the student's hidden state before and after asking a question and find it is predictive of the trajectory's final correctness, even before generating the teacher's answer. This suggests there is a meaningful signal from the self-diagnosis that occurs during question generation rather than information transfer from the teacher. We then frame question-asking as a sequential decision problem, using this probe as a quality score, and define a gating policy to ask questions that maximize likelihood of correctness. We find that the success of question-asking as an intervention is largely dependent on the model's self-consistency. Our empirical results show a gap between detection and recovery; while our gating policy captures model correctness and uncertainty, interventions are equally likely to harm correct trajectories as they are to recover incorrect ones. This gap between diagnosis and correction has broader implications on language models' capacity for self-refinement under uncertainty.
查看此版本解读 →查看此版本原文 ↗