不确定性下通过策略信息分配理解LLM中的推理
Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty
AI总结：
本文提出一个信息论框架，将推理分解为程序推进和认知外化（不确定性标记级外化），证明零散外化能在无显式错误触发时恢复收敛，并通过实验表明小规模SFT即可调控该能力，从而将推理重新定义为不确定性下的策略信息分配。
摘要：
LLM 经常表现出“啊哈”时刻，例如在“Wait”等标记后进行自我修正，但其潜在机制仍不清楚。标准 LLM 主要通过无声发散崩溃，即轨迹偏离正确答案但仍保持局部连贯，因此没有显式错误触发反应性自我修正。我们引入一个信息论框架，将推理分解为程序推进和认知外化（不确定性的标记级外化），并证明零散外化能在没有显式错误触发的情况下恢复向正确答案的收敛。实验上，一个最小的怀疑线索即可恢复失败的轨迹，小规模 SFT 足以灌输或抑制这种能力，这表明强推理更少依赖于非凡的内在机制，而更多依赖于外化不确定性的语言习惯。我们的框架将推理重新定义为不确定性下的策略信息分配，为理解和推进 LLM 推理提供了新视角。
英文摘要：
LLMs often exhibit Aha moments such as self-correction after tokens like "Wait," yet the underlying mechanism remains unclear. Standard LLMs collapse mainly through silent divergence, where trajectories drift from the correct answer yet remain locally coherent, so no explicit error triggers reactive self-correction. We introduce an information-theoretic framework that separates reasoning into procedural advancement and epistemic verbalization, the token-level externalization of uncertainty, and prove that sporadic verbalization restores convergence toward the correct answer even without explicit error triggers. Empirically, a minimal doubt cue recovers failed trajectories, and small-scale SFT suffices to instill or suppress this capability, suggesting that strong reasoning hinges less on an extraordinary inner mechanism than on the linguistic habit of externalizing uncertainty. Our framework recasts reasoning as strategic information allocation under uncertainty, offering a new lens for understanding and advancing LLM reasoning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
