通过零空间约束缓解多语言序列知识编辑中的负干扰
Mitigating Negative Interference in Multilingual Sequential Knowledge Editing through Null-Space Constraints
AI总结：
针对多语言大语言模型序列知识编辑存在的参数负干扰问题，提出零空间约束框架LangEdit，通过将各语言参数更新投影至正交补空间保证更新独立性，在多架构多语言多任务上优于现有方法，可实现高效准确的多语言知识更新。
摘要：
在大语言模型（LLMs）中高效更新多语言知识，同时保持跨语言的事实表征一致性，仍是一项长期未解决的挑战。虽然为每种语言部署独立的编辑系统看似可行，但由于需要管理多个模型，该方法会产生高昂成本。更高效的方案是将所有语言的知识更新整合到统一模型中，但跨语言执行序列编辑往往会导致破坏性的参数干扰，严重降低多语言泛化能力和注入知识的准确性。为应对这一挑战，我们提出LangEdit——一种新型零空间约束框架，旨在精准隔离特定语言的知识更新。LangEdit的核心创新在于能够将每种语言的参数更新投影到先前更新子空间的正交补空间上，该方法在数学上保证了更新的独立性，同时保留多语言泛化能力。我们在三种模型架构、六种语言和四项下游任务上开展了全面评估，结果表明LangEdit有效缓解了参数干扰，性能优于现有最先进的编辑方法。研究结果凸显了其在LLMs中实现高效、准确多语言知识更新的潜力。代码可在https://github.com/VRCMF/LangEdit.git获取。
英文摘要：
Efficiently updating multilingual knowledge in large language models (LLMs), while preserving consistent factual representations across languages, remains a long-standing and unresolved challenge. While deploying separate editing systems for each language might seem viable, this approach incurs substantial costs due to the need to manage multiple models. A more efficient solution involves integrating knowledge updates across all languages into a unified model. However, performing sequential edits across languages often leads to destructive parameter interference, significantly degrading multilingual generalization and the accuracy of injected knowledge. To address this challenge, we propose LangEdit, a novel null-space constrained framework designed to precisely isolate language-specific knowledge updates. The core innovation of LangEdit lies in its ability to project parameter updates for each language onto the orthogonal complement of previous updated subspaces. This approach mathematically guarantees update independence while preserving multilingual generalization capabilities. We conduct a comprehensive evaluation across three model architectures, six languages, and four downstream tasks, demonstrating that LangEdit effectively mitigates parameter interference and outperforms existing state-of-the-art editing methods. Our results highlight its potential for enabling efficient and accurate multilingual knowledge updates in LLMs. The code is available at https://github.com/VRCMF/LangEdit.git.
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。
