推理使语言模型对齐人类认知
Reasoning aligns language models to human cognition
AI总结：
本研究通过主动概率推理任务揭示语言模型与人类在不确定性决策中的差异，发现延长推理能显著提升推理性能，但对信息获取影响有限。
摘要：
语言模型在不确定性下做决定是否像人类一样，链式推理（CoT）推理在底层决策过程中起什么作用？我们引入了一个主动概率推理任务，清晰地将采样（积极获取证据）与推理（整合证据以做出决策）分开。在近最优参考策略下对人类和一系列现代大型语言模型进行基准测试，揭示出一致的模式：延长推理是强性能的关键决定因素，推动推理的大幅改进，并产生令人惊讶的人类般的信念轨迹，同时仅在主动采样方面产生适度的改进。为了解释这些差异，我们拟合了一个机械模型，通过四个可解释的潜在变量：记忆、策略、选择偏见和遮蔽意识，捕捉系统性偏离最优行为。该模型将人类和模型置于共享的低维认知空间中，再现了跨代理的行为特征，并展示了链式推理如何使语言模型朝着人类般的证据积累和信念到选择映射的领域转变，加强推理的对齐，同时在信息获取方面留下持久的差距。
英文摘要：
Do language models make decisions under uncertainty like humans do, and what role does chain-of-thought (CoT) reasoning play in the underlying decision process? We introduce an active probabilistic reasoning task that cleanly separates sampling (actively acquiring evidence) from inference (integrating evidence toward a decision). Benchmarking humans and a broad set of contemporary large language models against near-optimal reference policies reveals a consistent pattern: extended reasoning is the key determinant of strong performance, driving large gains in inference and producing belief trajectories that become strikingly human-like, while yielding only modest improvements in active sampling. To explain these differences, we fit a mechanistic model that captures systematic deviations from optimal behavior via four interpretable latent variables: memory, strategy, choice bias, and occlusion awareness. This model places humans and models in a shared low-dimensional cognitive space, reproduces behavioral signatures across agents, and shows how chain-of-thought shifts language models toward human-like regimes of evidence accumulation and belief-to-choice mapping, tightening alignment in inference while leaving a persistent gap in information acquisition.
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。
