快思考，错思考：直觉性调节LLM在政策评估中的反事实推理
Thinking Fast, Thinking Wrong: Intuitiveness Modulates LLM Counterfactual Reasoning in Policy Evaluation
AI总结：
本研究构建了一个基于经济学和社会科学实证案例的基准，通过8000次实验评估大型语言模型在政策评估中的反事实推理，发现链式思维提示在反直觉案例中效果显著减弱，且直觉性是主导因素，表明模型存在知识-推理分离。
摘要：
大型语言模型（LLM）越来越多地用于因果和反事实推理，但它们在现实世界政策评估中的可靠性仍未得到充分探索。我们构建了一个包含40个实证政策评估案例的基准，这些案例来自经济学和社会科学，每个案例都基于同行评审的证据，并根据直觉性进行分类——即实证结果是否符合（明显）、相对于（模糊）或违背（反直觉）常见的先验预期。我们评估了四个前沿LLM，采用五种提示策略，进行了8000次实验试验，并使用混合效应逻辑回归分析结果。我们的发现揭示了三个关键结果：（1）链式思维（CoT）悖论，即链式思维提示在明显案例上显著提升性能，但在反直觉案例上这种收益大幅减弱（交互OR = 0.278，p < 0.001）；（2）直觉性是主导因素，案例层面的方差超过模型选择或提示策略（ICC = 0.671）；（3）知识-推理分离，基于引用的熟悉度与准确性无关（p = 0.84），表明模型拥有相关知识，但当结果与直觉相悖时无法利用这些知识进行推理。我们通过双过程理论（系统1与系统2）的视角来框架这些结果，并认为当前LLM的“慢思考”仅实现了对直觉先验的部分抑制——产生了深思熟虑推理的形式，但未能完全实现其实质。
英文摘要：
Large language models (LLMs) are increasingly used for causal and counterfactual reasoning, yet their reliability in real-world policy evaluation remains underexplored. We construct a benchmark of 40 empirical policy evaluation cases drawn from economics and social science, each grounded in peer-reviewed evidence and classified by intuitiveness -- whether the empirical finding aligns with (obvious), is unclear relative to (ambiguous), or contradicts (counter-intuitive) common prior expectations. We evaluate four frontier LLMs across five prompting strategies with 8,000 experimental trials and analyze the results using mixed-effects logistic regression. Our findings reveal three key results: (1) a chain-of-thought (CoT) paradox, where chain-of-thought prompting dramatically improves performance on obvious cases but this benefit is substantially attenuated on counter-intuitive ones (interaction OR = 0.278, $p < 0.001$); (2) intuitiveness as the dominant factor, with case-level variance exceeding that of model choice or prompting strategy (ICC = 0.671); and (3) a knowledge-reasoning dissociation, where citation-based familiarity is unrelated to accuracy ($p = 0.84$), suggesting models possess relevant knowledge but fail to reason with it when findings contradict intuition. We frame these results through the lens of dual-process theory (System 1 vs. System 2) and argue that current LLMs' "slow thinking" achieves only partial inhibition of intuitive priors -- producing the form of deliberative reasoning without fully delivering its substance.
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。
