Standard fine-tuning is considered not as effective as specialized methods for model editing due to its comparatively poor performance. However, it is simple, agnostic to the architectural details of the model being edited, and able to leverage advances in standard training techniques with no additional work (e.g., black-box PEFT for computational efficiency), making it an appealing choice for a model editor. In this work, we show that standard fine-tuning alone can yield competitive model editing performance with two minor modifications. First, we optimize the conditional likelihood rather than the full likelihood. Second, in addition to the typical practice of training on randomly paraphrased edit prompts to encourage generalization, we also train on random or similar unedited facts to encourage locality. Our experiments on the ZsRE and CounterFact datasets demonstrate that these simple modifications allow standard fine-tuning to match or outperform highly specialized editors in terms of edit score.

翻译：标准微调因其相对较差的性能，通常被认为不如专门的模型编辑方法有效。然而，该方法简单、无需了解被编辑模型的结构细节，并且能够直接利用标准训练技术的最新进展而无需额外工作（例如，采用黑盒参数高效微调技术以提升计算效率），这使其成为模型编辑中颇具吸引力的选择。在本研究中，我们证明仅通过两项微小的修改，标准微调本身即可实现具有竞争力的模型编辑性能。首先，我们优化条件似然而非完整似然。其次，除了通常采用的通过随机释义的编辑提示进行训练以促进泛化外，我们还对随机或相似的未编辑事实进行训练以增强局部性。我们在ZsRE和CounterFact数据集上的实验表明，这些简单的修改使得标准微调在编辑得分方面能够匹配甚至超越高度专业化的编辑方法。