Large language models (LLMs) rely on internal knowledge to solve many downstream tasks, making it crucial to keep them up to date. Since full retraining is expensive, prior work has explored efficient alternatives such as model editing and parameter-efficient fine-tuning. However, these approaches often break down in practice due to poor generalization across inputs, limited stability, and knowledge conflict. To address these limitations, we propose the CoRSA (Conflict-Resolving and Sharpness-Aware Minimization) training framework, a parameter-efficient, holistic approach for knowledge editing with multiple updates. CoRSA tackles multiple challenges simultaneously: it improves generalization to different input forms and enhances stability across multiple updates by minimizing loss curvature, and resolves conflicts by maximizing the margin between new and prior knowledge. Across three widely used fact editing benchmarks, CoRSA achieves significant gains in generalization, outperforming baselines with average absolute improvements of 12.42% over LoRA and 10% over model editing methods. With multiple updates, it maintains high update efficacy while reducing catastrophic forgetting by 27.82% compared to LoRA. CoRSA also generalizes to the code domain, outperforming the strongest baseline by 5.48% Pass@5 in update efficacy.

翻译：大型语言模型（LLM）依赖内部知识解决众多下游任务，因此保持其知识时效性至关重要。由于完全重训练成本高昂，先前研究探索了模型编辑与参数高效微调等高效替代方案。然而，这些方法在实践中常因输入泛化能力不足、更新稳定性有限及知识冲突等问题而失效。为突破这些局限，我们提出CoRSA（冲突消解与锐度感知最小化）训练框架——一种面向多重更新、参数高效且系统化的知识编辑方法。CoRSA同步应对多重挑战：通过最小化损失曲率提升对不同输入形式的泛化能力与多重更新下的稳定性，并通过最大化新旧知识间隔实现冲突消解。在三个广泛使用的事实编辑基准测试中，CoRSA在泛化性能上取得显著提升，平均绝对改进幅度较LoRA提升12.42%，较模型编辑方法提升10%。在多重更新场景下，其保持高更新效能的同时，相比LoRA将灾难性遗忘降低了27.82%。CoRSA还可泛化至代码领域，在更新效能上以Pass@5指标超越最强基线5.48%。