arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.12813cs.CLcs.AI
收藏

检查事实并再次尝试:利用外部知识和自动反馈改进大语言模型

Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback

Microsoft Research(微软研究院);Columbia University(哥伦比亚大学)

Baolin Peng, Michel Galley, Pengcheng He, Hao Cheng, Yujia Xie, Yu Hu, Qiuyuan Huang, Lars Liden, Zhou Yu, Weizhu Chen, Jianfeng Gao

摘要:

诸如ChatGPT之类的大语言模型(LLM)能够为许多下游任务生成类似人类的流畅响应,例如,以任务为导向的对话和问答。然而,将LLM应用于现实世界的关键任务应用程序仍然具有挑战性,主要是因为它们倾向于产生幻觉,并且无法使用外部知识。本文提出了一种LLM增强器系统,它增加了一组即插即用模块的黑盒LLM。我们的系统使LLM生成基于外部知识的响应,例如,存储在特定任务的数据库中。它还迭代地修改LLM提示,以使用由效用函数生成的反馈来改善模型响应,例如,LLM生成的响应的真实性得分。LLM-Augmenter的有效性进行了实证验证两种类型的场景,面向任务的对话和开放域问答。LLM-Augmenter可以显着减少ChatGPT的幻觉,同时又不牺牲其响应的流畅性和信息量。我们公开源代码和模型。

英文摘要:

Large language models (LLMs), such as ChatGPT, are able to generate human-like, fluent responses for many downstream tasks, e.g., task-oriented dialog and question answering. However, applying LLMs to real-world, mission-critical applications remains challenging mainly due to their tendency to generate hallucinations and their inability to use external knowledge. This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules. Our system makes the LLM generate responses grounded in external knowledge, e.g., stored in task-specific databases. It also iteratively revises LLM prompts to improve model responses using feedback generated by utility functions, e.g., the factuality score of a LLM-generated response. The effectiveness of LLM-Augmenter is empirically validated on two types of scenarios, task-oriented dialog and open-domain question answering. LLM-Augmenter significantly reduces ChatGPT's hallucinations without sacrificing the fluency and informativeness of its responses. We make the source code and models publicly available.

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。

↑