评估模型编辑中的逆转诅咒
Evaluating the Reversal Curse in Model Editing
AI总结：
本文研究双向语言模型编辑，提出反向泛化指标并构建BAKE基准，发现多数编辑方法在反向评估中存在系统性缺陷，并分析逆转诅咒的成因及缓解策略。
摘要：
大型语言模型（LLMs）由于错误或过时的知识容易产生不期望的文本幻觉。由于重新训练LLMs资源密集，模型编辑日益受到关注。尽管出现了基准和方法，现有的单向编辑和评估范式未能探索逆转诅咒。在本文中，我们研究双向语言模型编辑，旨在提供严格的评估，以判断编辑后的LLMs能否双向回忆编辑知识。引入了反向泛化指标，并构建了名为BAKE（双向知识编辑评估）的基准，用于评估编辑后的模型能否在编辑的反向方向上回忆编辑知识。我们使用多种编辑方法和LLMs进行了大量实验。结果表明，尽管大多数编辑方法能够沿着修改方向准确回忆编辑事实，但在反向方向评估时，它们表现出显著的系统性缺陷。为了进一步研究逆转诅咒的根本原因并探索潜在的缓解策略，我们从三个角度进行了详细分析。我们的发现表明，尽管上下文学习（ICL）可以在一定程度上缓解逆转诅咒，但它缺乏连续性，受输入长度限制，并可能引入幻觉。因此，结合ICL和其他编辑方法的优势是开发新编辑范式的一个有前景的方向。
英文摘要：
Large language models (LLMs) are prone to hallucinate unintended text due to false or outdated knowledge. Since retraining LLMs is resource intensive, there has been a growing interest in model editing. Despite the emergence of benchmarks and approaches, existing unidirectional editing and evaluation paradigms have failed to explore the reversal curse. In this paper, we study bidirectional language model editing, aiming to provide a rigorous evaluation to assess if edited LLMs can recall the editing knowledge bidirectionally. A metric of reverse generalization is introduced and a benchmark dubbed Bidirectional Assessment for Knowledge Editing (BAKE) is constructed to evaluate if post-edited models can recall the edited knowledge in the reverse direction of editing. We conduct extensive experiments using a variety of editing methods and LLMs. The results show that while most editing methods are able to accurately recall editing facts along the modification direction, they exhibit substantial systematic deficiencies when evaluating in the reverse direction. To further investigate the underlying causes of reversal curse and to explore potential strategies for mitigation, a detailed analysis is conducted from three perspectives. Our findings reveal that although In-Context Learning (ICL) can mitigate the reversal curse to a certain extent, it lacks continuity, is limited by the input length, and may introduce hallucinations. Therefore, combining the advantages of ICL and other editing methods is a promising direction for developing new editing paradigms.
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。
