arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.10528cs.CLcs.AI
收藏

我们能否逐步验证以检测错误答案?

Can We Verify Step by Step for Incorrect Answer Detection?

The Hong Kong University of Science and Technology(香港科学与技术大学)

Xin Xu, Shizhe Diao, Can Yang, Yang Wang

AI总结:

为探究大语言模型推理链与输出准确性的关系,研究构建了跨五领域的R2PE基准,提出过程可分辨性得分框架,在45个子集上F1、AUC-PR均优于基线,还可提升开放域问答准确率。

摘要:

思维链(Chain-of-Thought, CoT)提示在提升大语言模型(LLMs)的推理能力方面取得了重大进展。以往研究开发了多种CoT扩展方法,主要聚焦于提升终端任务性能。此外,也有研究针对CoT中推理链的质量进行评估。这引出了一个引人关注的问题:能否通过仔细检查大语言模型生成的推理链来预测其输出的准确性?为回答这一研究问题,我们提出了R2PE基准,该基准专门用于探索跨五个不同领域的各类推理任务中推理链与性能之间的关系,旨在基于推理步骤衡量大语言模型最终输出的错误程度。为充分利用多条推理链中的信息,我们提出了过程可分辨性得分(process discernibility score, PDS)框架,该框架大幅优于答案检查基线。具体而言,在R2PE的全部45个子集上,该框架的F1得分平均提升5.1%,AUC-PR平均提升2.97%。我们进一步验证了PDS在提升开放域问答准确性方面的有效性。

英文摘要:

Chain-of-Thought (CoT) prompting has marked a significant advancement in enhancing the reasoning capabilities of large language models (LLMs). Previous studies have developed various extensions of CoT, which focus primarily on enhancing end-task performance. In addition, there has been research on assessing the quality of reasoning chains in CoT. This raises an intriguing question: Is it possible to predict the accuracy of LLM outputs by scrutinizing the reasoning chains they generate? To answer this research question, we introduce a benchmark, R2PE, designed specifically to explore the relationship between reasoning chains and performance in various reasoning tasks spanning five different domains. This benchmark aims to measure the falsehood of the final output of LLMs based on the reasoning steps. To make full use of information in multiple reasoning chains, we propose the process discernibility score (PDS) framework that beats the answer-checking baseline by a large margin. Concretely, this resulted in an average of $5.1\%$ increase in the F1 score and $2.97\%$ improvement in AUC-PR across all 45 subsets within R2PE. We further demonstrate our PDS's efficacy in advancing open-domain QA accuracy.

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。

↑