用事实击败有害刻板印象：基于RAG的反言论生成
Beating Harmful Stereotypes Through Facts: RAG-based Counter-speech Generation
AI总结：
针对现有反言论生成方法在可靠性和可扩展性上的不足，提出一个集成RAG流程的知识型生成框架，利用包含32,792篇文本的知识库，为8个目标群体生成可信反言论，并在MultiTarget-CONAN数据集上通过自动和人工评估验证了其优越性。
摘要：
反言论生成是许多专家活动的核心，例如事实核查和仇恨言论，用以对抗有害内容。然而，现有工作将反言论生成视为纯文本生成任务，主要基于大型语言模型或非政府组织专家。这些方法分别因生成的反驳文本的可靠性和连贯性有限，以及可扩展性不足，而显示出严重缺陷。为弥补这一差距，我们引入了一个新颖的框架，将反言论生成建模为知识型文本生成过程。我们的框架集成了先进的检索增强生成（RAG）流程，以确保为仇恨言论文献中确定的8个主要目标群体生成可信的反言论，包括女性、有色人种、残疾人、移民、穆斯林、犹太人、LGBT人士及其他。我们在联合国数字图书馆、EUR-Lex和欧盟基本权利机构的基础上构建了一个知识库，共包含32,792篇文本。我们使用MultiTarget-CONAN数据集，通过标准指标（即JudgeLM）和人工评估，实证评估了生成的反言论的质量。结果表明，我们的框架在两种评估中均优于标准的LLM基线和竞争性方法。所提出的框架和知识库为研究可信且合理的反言论生成（在仇恨言论及其他领域）铺平了道路。
英文摘要：
Counter-speech generation is at the core of many expert activities, such as fact-checking and hate speech, to counter harmful content. Yet, existing work treats counter-speech generation as pure text generation task, mainly based on Large Language Models or NGO experts. These approaches show severe drawbacks due to the limited reliability and coherence in the generated countering text, and in scalability, respectively. To close this gap, we introduce a novel framework to model counter-speech generation as knowledge-wise text generation process. Our framework integrates advanced Retrieval-Augmented Generation (RAG) pipelines to ensure the generation of trustworthy counter-speech for 8 main target groups identified in the hate speech literature, including women, people of colour, persons with disabilities, migrants, Muslims, Jews, LGBT persons, and other. We built a knowledge base over the United Nations Digital Library, EUR-Lex and the EU Agency for Fundamental Rights, comprising a total of 32,792 texts. We use the MultiTarget-CONAN dataset to empirically assess the quality of the generated counter-speech, both through standard metrics (i.e., JudgeLM) and a human evaluation. Results show that our framework outperforms standard LLM baselines and competitive approach, on both assessments. The resulting framework and the knowledge base pave the way for studying trustworthy and sound counter-speech generation, in hate speech and beyond.
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。
