arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.18344cs.CLcs.AIcs.LG
收藏

Chainpoll:一种高效的LLM幻觉检测方法

Chainpoll: A high efficacy method for LLM hallucination detection

Galileo Technologies Inc.(伽利略科技公司)

Robert Friel, Atindriyo Sanyal

AI总结:

本文提出ChainPoll幻觉检测方法,并构建RealHall基准数据集,实验表明其在所有基准上均优于现有方法,总体AUROC达0.781,同时引入Adherence和Correctness两个新指标。

摘要:

大型语言模型(LLMs)在生成连贯且与上下文相关的响应方面取得了显著进展。然而,幻觉——即不正确或缺乏根据的陈述——仍然普遍存在,这促使人们创建自动化指标来检测LLM输出中的这些问题。我们的贡献包括:引入ChainPoll,这是一种创新的幻觉检测方法,与同类方法相比表现出色;并发布RealHall,这是一个经过精炼的基准数据集集合,用于评估近期研究中的幻觉检测指标。在创建RealHall的过程中,我们评估了以往幻觉检测研究中的任务和数据集,并观察到其中许多并不适合当前使用的强大LLMs。为克服这一问题,我们选择了四个对现代LLMs具有挑战性且与现实世界场景相关的数据集。利用RealHall,我们将ChainPoll与近期研究中的众多幻觉检测指标进行了全面比较。我们的研究结果表明,ChainPoll在所有RealHall基准上均表现更优,总体AUROC达到0.781。这比次优的理论方法高出11%,比行业标准高出超过23%。此外,ChainPoll具有成本效益,并且比其他指标提供更高的透明度。我们引入两个新颖指标来评估LLM幻觉:Adherence和Correctness。Adherence与检索增强生成(Retrieval Augmented Generation)工作流相关,用于评估LLM在给定文档和上下文中的分析能力。相比之下,Correctness用于识别逻辑和推理错误。

英文摘要:

Large language models (LLMs) have experienced notable advancements in generating coherent and contextually relevant responses. However, hallucinations - incorrect or unfounded claims - are still prevalent, prompting the creation of automated metrics to detect these in LLM outputs. Our contributions include: introducing ChainPoll, an innovative hallucination detection method that excels compared to its counterparts, and unveiling RealHall, a refined collection of benchmark datasets to assess hallucination detection metrics from recent studies. While creating RealHall, we assessed tasks and datasets from previous hallucination detection studies and observed that many are not suitable for the potent LLMs currently in use. Overcoming this, we opted for four datasets challenging for modern LLMs and pertinent to real-world scenarios. Using RealHall, we conducted a comprehensive comparison of ChainPoll with numerous hallucination metrics from recent studies. Our findings indicate that ChainPoll outperforms in all RealHall benchmarks, achieving an overall AUROC of 0.781. This surpasses the next best theoretical method by 11% and exceeds industry standards by over 23%. Additionally, ChainPoll is cost-effective and offers greater transparency than other metrics. We introduce two novel metrics to assess LLM hallucinations: Adherence and Correctness. Adherence is relevant to Retrieval Augmented Generation workflows, evaluating an LLM's analytical capabilities within given documents and contexts. In contrast, Correctness identifies logical and reasoning errors.

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。

↑