通过贝叶斯突变自适应分割，实现长文本知识编辑的结构感知与一致性保持。
AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise
- 基于贝叶斯突变动态识别语义边界，取代固定窗口分块。
- 在数学推理、代码生成等任务上优于现有方法，保持生成连贯性。
- 适合需要精准修改长文本知识的开发者与研究者使用。
大型语言模型中复杂长文本知识的编辑仍面临生成连贯性难维持的挑战。现有自回归方法如AnyEdit虽缓解长度限制，但依赖固定窗口分块，忽略逻辑结构，影响一致性。为此，我们提出AnyEdit++，一种结构感知框架，包含贝叶斯分块（Bayes-Chunk）机制，基于贝叶斯突变动态识别语义边界。该方法建立在理论框架之上，确立两大原则：(1) 结构独立性——当锚点键几何正交时，跨段干扰最小化（我们的突变边界自然满足此条件，而固定窗口不满足）；(2) 因果局部性——在语义峰值处注入更新，相比任意切分点控制效果更优。在数学推理、代码生成和叙事任务上的广泛实验表明，AnyEdit++性能与鲁棒性均优于当前最优基线，验证了结构感知对有效长文本知识编辑的关键作用。
原文摘要 · Abstract (English)
Editing complex, long-form knowledge in Large Language Models remains a significant challenge due to the difficulty of maintaining generation coherence. Existing autoregressive methods like AnyEdit alleviate length constraints but rely on Fixed-window Chunking, which disregards logical structure and compromises consistency. To address this, we present AnyEdit++, a structure-aware framework incorporating Bayes-Chunk, an adaptive segmentation mechanism that dynamically identifies semantic boundaries based on Bayesian Surprise. We underpin this approach with a theoretical framework establishing two key principles: (1) Structural Independence: we prove that cross-segment interference is minimized when anchor keys are geometrically orthogonal (a condition naturally satisfied by our surprisal-based boundaries but violated by fixed windows), and (2) Causal Locality: we demonstrate that updates injected at these semantic peaks yield strictly superior control compared to arbitrary split points. Extensive experiments across mathematical reasoning, code generation, and narrative tasks demonstrate that AnyEdit++ achieves superior performance and robustness compared to state-of-the-art baselines, validating that structural awareness is critical for effective long-form knowledge editing.
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。