模型编辑会损害大语言模型的通用能力：正则化可解此难题
Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
AI总结：
该研究发现模型编辑提升大语言模型事实性时会损害其通用能力，通过分析成因提出基于权重相对变化的RECT正则化方法，可在保持94%以上编辑性能的同时显著缓解副作用。
摘要：
模型编辑是一种用更新后的知识编辑大语言模型（LLMs）的技术，无需耗费大量资源进行重训练即可缓解幻觉问题。当前的模型编辑方法虽能有效修改模型在特定关注领域的行为，却往往忽略了其对LLMs推理、自然语言推断、问答等通用能力可能造成的意外副作用。本文提出担忧：模型编辑在事实性上的提升，可能是以模型通用能力显著下降为代价的。我们通过在三个LLM上评估四种主流编辑方法、覆盖八项代表性任务，系统分析了这类副作用。大量实证实验表明，当前编辑方法很难同时提升LLMs的事实性并维持其通用能力。分析显示，副作用的成因是模型编辑过度改变了模型原始权重，导致对编辑事实的过拟合。为缓解该问题，本文提出了名为RECT（基于权重相对变化的正则化编辑方法）的方法，通过对权重更新的复杂度施加约束来正则化编辑后的权重更新量。评估结果显示，RECT能显著缓解编辑的副作用，同时仍能保持94%以上的编辑性能。
英文摘要：
Model editing is a technique that edits the large language models (LLMs) with updated knowledge to alleviate hallucinations without resource-intensive retraining. While current model editing methods can effectively modify a model's behavior within a specific area of interest, they often overlook the potential unintended side effects on the general abilities of LLMs such as reasoning, natural language inference, and question answering. In this paper, we raise concerns that model editing's improvements on factuality may come at the cost of a significant degradation of the model's general abilities. We systematically analyze the side effects by evaluating four popular editing methods on three LLMs across eight representative tasks. Our extensive empirical experiments show that it is challenging for current editing methods to simultaneously improve factuality of LLMs and maintain their general abilities. Our analysis reveals that the side effects are caused by model editing altering the original model weights excessively, leading to overfitting to the edited facts. To mitigate this, a method named RECT is proposed to regularize the edit update weights by imposing constraints on their complexity based on the RElative Change in weighT. Evaluation results show that RECT can significantly mitigate the side effects of editing while still maintaining over 94% editing performance.
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。
