AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise

• URL: http://arxiv.org/abs/2606.01053v1
• Date: Sun, 31 May 2026 06:48:43 GMT
• Title: AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise
• Abstract summary: We present AnyEdit++, a structure-aware framework incorporating Bayes-Chunk.<n>We show that AnyEdit++ achieves superior performance and robustness compared to state-of-the-art baselines.
• Score: 10.675226603704937
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models [49.67749928542536]
  Safety alignment of text-to-image (T2I) diffusion models aims to suppress harmful generations while preserving utility on benign prompts.<n>Recent methods often appear to deliver high safety with high utility, but this conclusion rests largely on coarse global utility metrics.<n>We show that when utility is measured with structured evaluation, this illusion breaks: onA (Text-to-Image Faithfulness evaluation with Question Answering)<n>We propose StructureAware Geometric Regularization (SAGE), a safety alignment objective that explicitly preserves embedding spread and inter-prompt relational structure.
  arXiv  Detail & Related papers  (2026-07-01T04:00:27Z)
• IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking [50.381430711141995]
  We introduce the Interleaved Structural Chain-of-Thought (IS-CoT) framework.<n>IS-CoT embeds a dynamic Plan-Write-Reflect cycle into the generation process.<n>We construct a high-quality dataset of interleaved reasoning traces via a multi-teacher pipeline and train IS-Writer-8B.
  arXiv  Detail & Related papers  (2026-06-08T16:31:00Z)
• AnchorSteer: Self-Discovered Concept Injection for Structure-Preserving Music Editing [14.255074251309168]
  AnchorSteer is a framework that disentangles tension by coupling structural anchoring with self-discovered semantic steering.<n>The proposed approach probes internal representations to extract interpretable, label-free concept vectors.<n>Experiments on ZoME-Bench and subjective tests show that the proposed framework outperforms both steering-only and anchoring-only baselines.
  arXiv  Detail & Related papers  (2026-05-29T09:25:55Z)
• The Labyrinth and the Thread: Rethinking Regularizations in Sequential Knowledge Editing for Large Language Models [15.376868559569623]
  We first analyze the empirical success of AlphaEdit and establish, via a rigorous optimization analysis, the formal equivalence between one-time and sequential editing.<n>We empirically confirm that many commonly used regularization strategies are unnecessary for reliable sequential updates.<n>Our work provides Ariadne's thread through the labyrinth of sequential editing, charting a path toward simpler, more interpretable, and dependable knowledge updates.
  arXiv  Detail & Related papers  (2026-05-26T08:07:25Z)
• Beyond the Covariance Trap: Unlocking Generalization in Same-Subject Knowledge Editing for Large Language Models [18.348253900450093]
  We show that models fail to recall updated knowledge when following user instructions, despite successfully recalling it in the original edited form.<n>We introduce RoSE (Robust Same-subject Editing), which employs Isotropic Geometric Alignment to minimize representational deviation and Hierarchical Knowledge Integration to smooth the optimization landscape.
  arXiv  Detail & Related papers  (2026-03-16T16:44:54Z)
• Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework [15.17681731375364]
  SeCuRepair is a semantics-aligned, curriculum-driven, and reasoning-enhanced framework for vulnerability repair.<n>At its core, SeCuRepair adopts a reason-then-edit paradigm, requiring the model to articulate why and how a vulnerability should be fixed.<n>SeCuRepair also moves beyond traditional supervised fine-tuning and employs semantics-aware reinforcement learning.
  arXiv  Detail & Related papers  (2025-10-01T15:09:27Z)
• DisProtEdit: Exploring Disentangled Representations for Multi-Attribute Protein Editing [48.819599672346136]
  DisProtEdit is a controllable protein editing framework that leverages dual-channel natural language supervision.<n>DisProtEdit explicitly separates semantic factors, enabling modular and interpretable control.
  arXiv  Detail & Related papers  (2025-06-17T06:12:18Z)
• Tady: A Neural Disassembler without Structural Constraint Violations [14.794789423601552]
  We introduce Tady, a novel neural disassembler featuring an improved model architecture and a dedicated post-processing algorithm.<n>We show that Tady effectively eliminates structural constraint violations and functions with high efficiency, while maintaining instruction-level accuracy.
  arXiv  Detail & Related papers  (2025-06-16T10:11:43Z)
• Tuning-Free Image Editing with Fidelity and Editability via Unified Latent Diffusion Model [60.82962950960996]
  We introduce UnifyEdit, a tuning-free method that performs diffusion latent optimization.<n>We develop two attention-based constraints: a self-attention (SA) preservation constraint for structural fidelity, and a cross-attention (CA) alignment constraint to enhance text alignment.<n>Our approach achieves a robust balance between structure preservation and text alignment across various editing tasks, outperforming other state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-04-08T01:02:50Z)
• DuCos: Duality Constrained Depth Super-Resolution via Foundation Model [56.88399488384106]
  We introduce DuCos, a novel depth super-resolution framework grounded in Lagrangian duality theory.<n>DuCos is the first to significantly improve generalization across diverse scenarios with foundation models as prompts.
  arXiv  Detail & Related papers  (2025-03-06T07:36:45Z)
• EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries [69.72012539060731]
  We introduce a theoretical framework for efficient knowledge editing (KE) in large language models (LLMs) We propose a novel task of event-based knowledge editing that pairs facts with event descriptions. We empirically demonstrate the superiority of event-based editing over the existing setting on resolving uncertainty in edited models.
  arXiv  Detail & Related papers  (2024-02-17T16:34:50Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.