在大语言模型中遗忘气候错误信息
Unlearning Climate Misinformation in Large Language Models
AI总结：
本文研究了LLMs在气候信息上的事实准确性，发现注入虚假信息可能不影响其他领域准确性，并比较了遗忘算法、微调和RAG，证明遗忘算法对细微概念性声明有效，为开发更可靠的LLMs提供了指导。
摘要：
关于气候变化的错误信息是应对人类面临的最严重威胁之一的关键障碍。本文研究了大语言模型（LLMs）在气候信息方面的事实准确性。我们使用标注为真/假的问答数据进行微调，并在与气候相关的声明上评估LLMs，比较了开源模型，评估它们对气候变化问题生成真实回答的能力。我们调查了被蓄意注入虚假气候信息的模型的可检测性，发现此类投毒可能不会影响模型在其他领域回答的准确性。此外，我们比较了遗忘算法、微调和检索增强生成（RAG）在将LLMs基于事实地锚定于气候变化主题上的有效性。我们的评估表明，尽管先前的研究认为遗忘算法在隐私场景下无效，但它们对细微差别的概念性声明是有效的。这些见解旨在指导开发更具事实可靠性的LLMs，并强调需要进一步的工作来保护LLMs免受错误信息攻击。
英文摘要：
Misinformation regarding climate change is a key roadblock in addressing one of the most serious threats to humanity. This paper investigates factual accuracy in large language models (LLMs) regarding climate information. Using true/false labeled Q&A data for fine-tuning and evaluating LLMs on climate-related claims, we compare open-source models, assessing their ability to generate truthful responses to climate change questions. We investigate the detectability of models intentionally poisoned with false climate information, finding that such poisoning may not affect the accuracy of a model's responses in other domains. Furthermore, we compare the effectiveness of unlearning algorithms, fine-tuning, and Retrieval-Augmented Generation (RAG) for factually grounding LLMs on climate change topics. Our evaluation reveals that unlearning algorithms can be effective for nuanced conceptual claims, despite previous findings suggesting their inefficacy in privacy contexts. These insights aim to guide the development of more factually reliable LLMs and highlight the need for additional work to secure LLMs against misinformation attacks.
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。
