发现大模型顺序知识编辑无需复杂正则化，稳定更新可自然实现。
The Labyrinth and the Thread: Rethinking Regularizations in Sequential Knowledge Editing for Large Language Models
- 通过优化分析证明单次与顺序编辑等价，稳定性源于正确处理累积约束。
- 实验证明多数常用正则化策略对可靠更新并非必要。
- 支持冲突编辑的鲁棒处理，适合需要持续更新知识的场景。
大型语言模型中顺序编辑结构化知识可实现针对性事实更新而无需重训练，但现有方法常依赖复杂的正则化或约束机制，其必要性尚不明确。本文系统研究了有效且稳定的顺序编辑机制。首先，通过严格的优化分析，确立了AlphaEdit经验成功背后的理论依据，并证明单次编辑与顺序编辑在形式上等价。基于此，将该等价关系推广至更广泛的编辑目标，表明稳定性源于对累积编辑约束的恰当建模，而非专门的正则化或零空间操作。实证结果表明，许多常用的正则化策略对可靠顺序更新并非必需。此外，我们的框架进一步扩展以应对冲突编辑，确保在矛盾更新下仍具鲁棒性和一致性。本工作为顺序编辑提供了清晰路径，使知识更新更简单、可解释且可靠。代码已公开于 https://github.com/Wangzzzzzzzz/OTE-SE-Alignment。
原文摘要 · Abstract (English)
Sequential editing of structured knowledge in large language models allows targeted factual updates without retraining, yet existing methods often rely on complex regularization or constraint mechanisms whose necessity remains unclear. In this work, we systematically investigate the mechanisms underlying effective and stable sequential editing. Specifically, we first analyze the empirical success of AlphaEdit and establish, via a rigorous optimization analysis, the formal equivalence between one-time and sequential editing. Building on this insight, we generalize the equivalence to a broader class of editing objectives, demonstrating that stability emerges naturally from properly accounting for accumulated editing constraints, rather than from specialized regularization or null-space operations. We empirically confirm that many commonly used regularization strategies are unnecessary for reliable sequential updates. Furthermore, we extend our framework to handle conflicting edits, ensuring robust and consistent behavior under contradictory updates. Ultimately, our work provides Ariadne's thread through the labyrinth of sequential editing, charting a path toward simpler, more interpretable, and dependable knowledge updates. Our code is available at https://github.com/Wangzzzzzzzz/OTE-SE-Alignment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。