用模型自信度加权投票，少抽样本也能更准答对推理题
Confidence Improves Self-Consistency in LLMs
- 基于模型自身信心得分加权投票，筛选高可信推理路径
- 平均减少40%以上采样量，仍保持更高准确率
- 证明大模型能自判输出正确性，适合推理优化研究者
自一致性解码通过采样多种推理路径并选择最频繁的答案来提升大模型在推理任务上的表现。然而，该方法计算开销大，需大量（长序列）路径采样才能提高正确答案成为高频结果的概率。为此，我们提出置信度引导的自一致性（CISC），直接利用模型输出的置信度分数进行加权多数投票。通过优先考虑高置信度路径，CISC能在显著更小的采样规模下识别正确答案。在九个模型和四个数据集上的实验表明，CISC几乎在所有配置中均优于传统自一致性，平均减少超过40%的推理路径需求。此外，我们引入了问题内置信度评估，发现标准评估方法对区分同一问题的正确与错误答案效果不佳。事实上，最校准的置信度方法反而在CISC中表现最差。最后，我们的结果和分析表明，大模型能够有效判断自身输出的正确性，为相关争论提供了新证据。
原文摘要 · Abstract (English)
Self-consistency decoding enhances LLMs' performance on reasoning tasks by sampling diverse reasoning paths and selecting the most frequent answer. However, it is computationally expensive, as sampling many of these (lengthy) paths is required to increase the chances that the correct answer emerges as the most frequent one. To address this, we introduce Confidence-Informed Self-Consistency (CISC). CISC performs a weighted majority vote based on confidence scores obtained directly from the model. By prioritizing high-confidence paths, it can identify the correct answer with a significantly smaller sample size. When tested on nine models and four datasets, CISC outperforms self-consistency in nearly all configurations, reducing the required number of reasoning paths by over 40% on average. In addition, we introduce the notion of within-question confidence evaluation, after showing that standard evaluation methods are poor predictors of success in distinguishing correct and incorrect answers to the same question. In fact, the most calibrated confidence method proved to be the least effective for CISC. Lastly, beyond these practical implications, our results and analyses show that LLMs can effectively judge the correctness of their own outputs, contributing to the ongoing debate on this topic.
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。