Better Call SAUL：利用生成正则化实现流畅且一致的语言模型编辑
Better Call SAUL: Fluent and Consistent Language Model Editing with Generation Regularization
AI总结：
本文提出SAUL模型编辑方法，通过句子拼接与增强随机事实进行生成正则化，在保持生成质量的同时以更低计算开销实现优于现有方法的编辑效果。
摘要：
为确保大型语言模型包含最新知识，需要定期对其进行更新。然而，模型编辑具有挑战性，因为它可能还会影响与新数据无关的知识。最先进的方法识别与特定知识相关的参数，然后通过直接权重更新来修改这些参数。然而，这些定位并编辑的方法存在计算开销大且缺乏理论验证的问题。相比之下，直接在请求的编辑上微调模型会影响模型在无关知识上的行为，并显著损害模型的生成流畅性和一致性。为应对这些挑战，我们提出SAUL，一种精简的模型编辑方法，它使用带有增强随机事实的句子拼接进行生成正则化。在三个模型编辑基准上的评估表明，SAUL是一种实用且可靠的模型编辑解决方案，在保持生成质量并降低计算开销的同时，优于最先进的方法。
英文摘要：
To ensure large language models contain up-to-date knowledge, they need to be updated regularly. However, model editing is challenging as it might also affect knowledge that is unrelated to the new data. State-of-the-art methods identify parameters associated with specific knowledge and then modify them via direct weight updates. However, these locate-and-edit methods suffer from heavy computational overhead and lack theoretical validation. In contrast, directly fine-tuning the model on requested edits affects the model's behavior on unrelated knowledge, and significantly damages the model's generation fluency and consistency. To address these challenges, we propose SAUL, a streamlined model editing method that uses sentence concatenation with augmented random facts for generation regularization. Evaluations on three model editing benchmarks show that SAUL is a practical and reliable solution for model editing outperforming state-of-the-art methods while maintaining generation quality and reducing computational overhead.
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。
