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 2402.02420cs.CLcs.AI
收藏

大语言模型的事实性:一项综述

Factuality of Large Language Models: A Survey

Monash University(莫纳什大学);Google(谷歌公司);Sofia University(索非亚大学);MBZUAI(穆罕默德·本·扎耶德人工智能大学)

Yuxia Wang, Minghan Wang, Muhammad Arslan Manzoor, Fei Liu, Georgi Georgiev, Rocktim Jyoti Das, Preslav Nakov

AI总结:

本综述针对大语言模型回复存在事实错误、限制实际应用的问题,批判性分析现有研究,梳理事实性提升的挑战、成因与潜在方案,分析开放式生成的自动事实性评估障碍,并展望未来研究方向。

摘要:

大语言模型(Large Language Models,LLMs),尤其是经过指令微调用于对话的大语言模型,已成为我们日常生活的一部分。它们通过在单一平台为各类问题提供直接答案,将人们从多源信息搜索、提取与整合的流程中解放出来。遗憾的是,在诸多场景下,LLM的回复存在事实错误,这限制了其在现实场景中的适用性。因此,评估与提升LLMs事实性的研究近期受到了广泛关注。在本综述中,我们批判性地分析了现有研究,旨在识别核心挑战及其成因,指出提升LLMs事实性的潜在解决方案,并分析开放式文本生成场景下自动化事实性评估面临的障碍。我们还对未来研究的方向进行了展望。

英文摘要:

Large language models (LLMs), especially when instruction-tuned for chat, have become part of our daily lives, freeing people from the process of searching, extracting, and integrating information from multiple sources by offering a straightforward answer to a variety of questions in a single place. Unfortunately, in many cases, LLM responses are factually incorrect, which limits their applicability in real-world scenarios. As a result, research on evaluating and improving the factuality of LLMs has attracted a lot of attention recently. In this survey, we critically analyze existing work with the aim to identify the major challenges and their associated causes, pointing out to potential solutions for improving the factuality of LLMs, and analyzing the obstacles to automated factuality evaluation for open-ended text generation. We further offer an outlook on where future research should go.

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。

↑