arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.14952cs.CLcs.AI
收藏

面向在线错误信息的证据驱动检索增强响应生成

Evidence-Driven Retrieval Augmented Response Generation for Online Misinformation

University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Zhenrui Yue, Huimin Zeng, Yimeng Lu, Lanyu Shang, Yang Zhang, Dong Wang

AI总结:

针对在线错误信息,提出RARG方法,通过检索科学证据并利用RLHF对齐LLM生成礼貌且基于事实的反驳响应,实验证明其在域内外数据集上均优于基线。

摘要:

在线错误信息的泛滥对公众利益构成了重大威胁。尽管众多在线用户积极参与打击错误信息,但许多此类响应的特征是缺乏礼貌和支持性事实。作为一种解决方案,人们提出了文本生成方法来自动生成反错误信息响应。然而,现有方法通常以端到端方式进行训练,未利用外部知识,导致文本质量欠佳且响应过度重复。在本文中,我们提出了面向在线错误信息的检索增强响应生成(RARG),该方法从科学来源收集支持性证据,并基于这些证据生成反错误信息响应。具体而言,我们的RARG包含两个阶段:(1)证据收集,我们设计了一个检索流水线,利用包含超过1M篇学术文章的数据库来检索并重排证据文档;(2)响应生成,在此阶段我们通过对齐大型语言模型(LLMs),借助人类反馈强化学习(RLHF)来生成基于证据的响应。我们提出了一个奖励函数,以最大化对检索证据的利用,同时保持生成文本的质量,从而产生礼貌且基于事实的响应,明确反驳错误信息。为了证明我们方法的有效性,我们以COVID-19为例进行了研究,并在域内和跨域数据集上进行了大量实验,其中RARG通过生成高质量的反错误信息响应,持续优于基线方法。

英文摘要:

The proliferation of online misinformation has posed significant threats to public interest. While numerous online users actively participate in the combat against misinformation, many of such responses can be characterized by the lack of politeness and supporting facts. As a solution, text generation approaches are proposed to automatically produce counter-misinformation responses. Nevertheless, existing methods are often trained end-to-end without leveraging external knowledge, resulting in subpar text quality and excessively repetitive responses. In this paper, we propose retrieval augmented response generation for online misinformation (RARG), which collects supporting evidence from scientific sources and generates counter-misinformation responses based on the evidences. In particular, our RARG consists of two stages: (1) evidence collection, where we design a retrieval pipeline to retrieve and rerank evidence documents using a database comprising over 1M academic articles; (2) response generation, in which we align large language models (LLMs) to generate evidence-based responses via reinforcement learning from human feedback (RLHF). We propose a reward function to maximize the utilization of the retrieved evidence while maintaining the quality of the generated text, which yields polite and factual responses that clearly refutes misinformation. To demonstrate the effectiveness of our method, we study the case of COVID-19 and perform extensive experiments with both in- and cross-domain datasets, where RARG consistently outperforms baselines by generating high-quality counter-misinformation responses.

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。

↑