给推理步骤加可信度标签，自动发现语言模型的错误推理
Latent Veracity Inference for Identifying Errors in Stepwise Reasoning
- 用隐变量标记每步推理真假，通过搜索算法高效推断
- 在三个基准上准确识别逻辑、数学和常识错误
- 可零样本判断新问题，适合提升模型自纠错能力
链式思维（CoT）提升了语言模型的能力与透明度，但推理链中可能包含错误陈述，影响性能与可信度。为此，我们为每个推理步骤引入一个隐式可信度（正确性）变量。为高效探索这一扩展空间，提出可信度搜索（VS），一种基于语言模型对可信度与最终答案联合似然的离散搜索算法，将其作为代理奖励，实现原本难以计算的后验分布推断。该方法支持对渐近可信度推断（AVI）机器进行监督微调，生成伪标签。AVI可泛化至未见场景，实现准确的零样本可信度推断。实验证明，VS在逻辑（ProntoQA）、数学（GSM8K）和常识（CommonsenseQA）推理基准上均能可靠识别错误，且AVI达到相近的零样本准确率。最后，展示了隐式可信度推断在自我修正与自我改进中的反馈价值。
原文摘要 · Abstract (English)
Chain-of-Thought (CoT) reasoning has advanced the capabilities and transparency of language models (LMs); however, reasoning chains can contain inaccurate statements that reduce performance and trustworthiness. To address this, we propose to augment each reasoning step in a CoT with a latent veracity (or correctness) variable. To efficiently explore this expanded space, we introduce Veracity Search (VS), a discrete search algorithm over veracity assignments. It performs otherwise intractable inference in the posterior distribution over latent veracity values by leveraging the LM's joint likelihood over veracity and the final answer as a proxy reward. This efficient inference-time verification method facilitates supervised fine-tuning of an Amortized Veracity Inference (AVI) machine by providing pseudo-labels for veracity. AVI generalizes VS, enabling accurate zero-shot veracity inference in novel contexts. Empirical results demonstrate that VS reliably identifies errors in logical (ProntoQA), mathematical (GSM8K), and commonsense (CommonsenseQA) reasoning benchmarks, with AVI achieving comparable zero-shot accuracy. Finally, we demonstrate the utility of latent veracity inference for providing feedback during self-correction and self-improvement.
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。