学习与去学习：解决多语言大语言模型中的错误信息问题
Learn and Unlearn: Addressing Misinformation in Multilingual LLMs
AI总结：
该研究针对多语言大语言模型中有害信息跨语言传播的问题，发现仅针对英文的标准去学习方法效果有限，提出需同时处理英文和有害数据原语言的有害响应，为提升多语言LLM安全性提供了策略方向。
摘要：
本文研究了有害信息在多语言大语言模型（LLMs）中的传播情况，并评估了各类去学习方法的效果。我们证明，虚假信息无论以何种语言存在，一旦通过训练数据引入这些模型，就会跨不同语言传播，损害生成内容的完整性与可靠性。研究发现，通常聚焦于英文数据的标准去学习技术，不足以缓解多语言场景下有害内容的传播，甚至可能无意中强化跨语言的有害内容。我们表明，只有同时处理英文以及有害数据原始语言中的有害响应，才能有效消除所有语言下的有害生成内容。这凸显了制定综合去学习策略的关键必要性——这类策略需考虑现代LLMs的多语言特性，以提升其在多元语言环境中的安全性与可靠性。
英文摘要：
This paper investigates the propagation of harmful information in multilingual large language models (LLMs) and evaluates the efficacy of various unlearning methods. We demonstrate that fake information, regardless of the language it is in, once introduced into these models through training data, can spread across different languages, compromising the integrity and reliability of the generated content. Our findings reveal that standard unlearning techniques, which typically focus on English data, are insufficient in mitigating the spread of harmful content in multilingual contexts and could inadvertently reinforce harmful content across languages. We show that only by addressing harmful responses in both English and the original language of the harmful data can we effectively eliminate generations for all languages. This underscores the critical need for comprehensive unlearning strategies that consider the multilingual nature of modern LLMs to enhance their safety and reliability across diverse linguistic landscapes.
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。
