发现大模型在推理时边生成步骤边计算答案，过程真实可信。
LLMs Faithfully and Iteratively Compute Answers During CoT: A Systematic Analysis With Multi-step Arithmetics
- 模型在生成思维链过程中实时计算子答案
- 答案并非输入后立即确定，而是逐步推导得出
- 适合研究模型推理机制与可解释性的人参考
本研究系统分析了大语言模型（LLMs）在执行链式思维（CoT）推理时的内部信息流动。重点关注思维链解释与最终答案之间的忠实度，探究：(i) 模型答案何时（预）确定，是在思维链开始前还是之后；(ii) 思维链中的信息对最终答案是否具有因果影响。通过控制变量的算术任务实验，揭示了LLMs具有一套系统的内部推理机制：模型在输入后并未立即确定答案，而是在生成推理链的同时逐步计算（子）答案。因此，生成的推理链可视为模型内部计算过程的真实反映。
原文摘要 · Abstract (English)
This study investigates the internal information flow of large language models (LLMs) while performing chain-of-thought (CoT) style reasoning. Specifically, with a particular interest in the faithfulness of the CoT explanation to LLMs' final answer, we explore (i) when the LLMs' answer is (pre)determined, especially before the CoT begins or after, and (ii) how strongly the information from CoT specifically has a causal effect on the final answer. Our experiments with controlled arithmetic tasks reveal a systematic internal reasoning mechanism of LLMs. They have not derived an answer at the moment when input was fed into the model. Instead, they compute (sub-)answers while generating the reasoning chain on the fly. Therefore, the generated reasoning chains can be regarded as faithful reflections of the model's internal computation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。