解码仇恨：探究语言模型对仇恨言论的反应
Decoding Hate: Exploring Language Models' Reactions to Hate Speech
AI总结：
本文通过定性分析比较七个主流LLM对仇恨言论及政治正确包装形式的反应，并提出微调与指南护栏等缓解生成仇恨言论的策略。
摘要：
仇恨言论是一种有害的在线表达形式，通常表现为贬损性帖子。它在数字环境中构成重大风险。随着大型语言模型（LLM）的兴起，鉴于这些模型在大量未经审核的互联网数据上进行训练，人们担心它们可能复制仇恨言论模式。理解LLM如何回应仇恨言论，对于负责任地部署它们至关重要。然而，迄今为止，关于LLM对仇恨言论行为的比较研究仍然有限。本文研究了七个最先进LLM（LLaMA 2、Vicuna、LLaMA 3、Mistral、GPT-3.5、GPT-4和Gemini Pro）对仇恨言论的反应。通过定性分析，我们旨在揭示这些模型产生的反应谱系，突出它们处理仇恨言论输入的能力。我们还讨论了缓解LLM生成仇恨言论的策略，特别是通过微调和指南护栏。最后，我们探究了这些模型对以政治正确语言包装的仇恨言论的反应。
英文摘要：
Hate speech is a harmful form of online expression, often manifesting as derogatory posts. It is a significant risk in digital environments. With the rise of Large Language Models (LLMs), there is concern about their potential to replicate hate speech patterns, given their training on vast amounts of unmoderated internet data. Understanding how LLMs respond to hate speech is crucial for their responsible deployment. However, the behaviour of LLMs towards hate speech has been limited compared. This paper investigates the reactions of seven state-of-the-art LLMs (LLaMA 2, Vicuna, LLaMA 3, Mistral, GPT-3.5, GPT-4, and Gemini Pro) to hate speech. Through qualitative analysis, we aim to reveal the spectrum of responses these models produce, highlighting their capacity to handle hate speech inputs. We also discuss strategies to mitigate hate speech generation by LLMs, particularly through fine-tuning and guideline guardrailing. Finally, we explore the models' responses to hate speech framed in politically correct language.
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。
