AI RESEARCH
AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise
arXiv CS.AI
•
ArXi:2606.01053v1 Announce Type: new 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.