拆解大模型自我修正能力，发现自信与批判的权衡关系。
Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs
- 将自我修正分解为自信修正和批判性纠错两类能力
- 发现不同模型在两类能力上表现差异显著，且存在此消彼长现象
- 通过调整微调数据格式，可同时提升两种能力并提高修正后准确率
大型语言模型能自我修正生成结果，但修正后准确率下降的现象也普遍存在。为深入理解自我修正机制，本文将其分解为‘信心’（对正确答案有把握进行修正）和‘批判’（将错误答案转为正确）两类能力，并从概率角度提出两项评估指标及一项综合指标。基于此，我们开展大量实验，发现不同模型表现出明显差异：部分模型更自信，部分更善于批判；通过提示词或上下文学习操控修正行为时，两类能力存在此消彼长的权衡。此外，我们提出一种简单高效的策略——转换监督微调（SFT）数据格式，该方法在两类能力上均优于原始SFT，且修正后准确率显著提升。代码将公开于GitHub。
原文摘要 · Abstract (English)
Large Language Models (LLMs) can correct their self-generated responses, but a decline in accuracy after self-correction is also witnessed. To have a deeper understanding of self-correction, we endeavor to decompose, evaluate, and analyze the self-correction behaviors of LLMs. By enumerating and analyzing answer correctness before and after self-correction, we decompose the self-correction capability into confidence (being confident to correct answers) and critique (turning wrong answers to correct) capabilities, and propose two metrics from a probabilistic perspective to measure these 2 capabilities, along with another metric for overall self-correction capability evaluation. Based on our decomposition and evaluation metrics, we conduct extensive experiments and draw some empirical conclusions. For example, we find different models can exhibit distinct behaviors: some models are confident while others are more critical. We also find the trade-off between the two capabilities (i.e. improving one can lead to a decline in the other) when manipulating model self-correction behavior by prompts or in-context learning. Further, we find a simple yet efficient strategy to improve self-correction capability by transforming Supervision Fine-Tuning (SFT) data format, and our strategy outperforms vanilla SFT in both capabilities and achieves much higher accuracy after self-correction. Our code will be publicly available on GitHub.
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。