paper-with-me

Papers

HyperPatch: Sequential Knowledge Editing Under n-ary Structural Drift

2026-06-02 · Yu-Kai Chan, Wen-Sheng Lien, Dong-Ting Yao, Bo-Kai Ruan, Kwan-Yeung Lin, Hong-Han Shuai, Meng-Fen Chiang arxiv

Large Language Models (LLMs) rely on Knowledge Editing (KE) to maintain temporal validity, yet real-world knowledge is inherently n-ary. We demonstrate that in non-stationary environments, sequential updates to complex relations induce N-ary Structural Drift, a phenomenon where the binary reification of n-ary events into triples fractures relational atomicity. This precipitates Structure-Conditioned Knowledge Transfer Failure, a systematic mis-grounding of the retriever frequently misdiagnosed as parametric hallucination. To tackle this, we propose HyperPatch, a parameter-preserving framework that reformulates sequential KE as a stability problem over hypergraph manifolds. HyperPatch preserves event integrity through three phases: (i) Structural Prior Initialization, establishing a topology-aware embedding space via contrastive learning on a Hypergraph Neural Network (HGNN) to capture high-order correlations; (ii) Sequential Topology Editing, utilizing a dual-stage mechanism that employs SimHash-based Topological Alignment for rapid conflict resolution and Topological LoRA Adaptation to track drift without backbone retraining; and (iii) Structure-Conditioned Reasoning, which integrates globally consistent evidence from fused linguistic and structural manifolds. On the MQuAKE-CF and MQuAKE-T benchmarks, HyperPatch achieves relative gains in Hop-wise Accuracy (H-Acc) of 96.24% and 21.06% over the strongest baseline, respectively. Further ablations demonstrate superior reliability under continuous n-ary update streams, whereas the standard KG-based variant suffers H-Acc collapses of up to 88.3% due to structural misalignment.

📄 PDF Abstract BibTeX arXiv:2606.03179

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learningknowledge editing

Similar Papers 제목 키워드 기반

Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse

2026-01-16 · Chi Zhang, Mengqi Zhang, Xiaotian Ye, Runxi Cheng 외 arxiv

Sequential knowledge editing in large language models often causes catastrophic collapse of the model's general abilities, especially for parameter-modifying methods. Existing approaches mitigate this issue through heuri…

knowledge editing

The Labyrinth and the Thread: Rethinking Regularizations in Sequential Knowledge Editing for Large Language Models

2026-05-26 · Zheng Wang, Kaixuan Zhang, Wanfang Chen, Jingwen Zhang 외 arxiv

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 r…

knowledge editing

DSCA: Dynamic Subspace Concept Alignment for Lifelong VLM Editing

2026-04-09 · Gyanendra Das, Sai Satyam Jena arxiv

Model editing aims to update knowledge to add new concepts and change relevant information without retraining. Lifelong editing is a challenging task, prone to disrupting previously learned concepts, especially for Visio…

knowledge editing

SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models

2025-10-19 · Chih-Kai Yang, Yen-Ting Piao, Tzu-Wen Hsu, Szu-Wei Fu 외 arxiv

Knowledge editing enables targeted updates without retraining, but prior work focuses on textual or visual facts, leaving abstract auditory perceptual knowledge underexplored. We introduce SAKE, the first benchmark for e…

knowledge editing

Energy-Regularized Sequential Model Editing on Hyperspheres

2025-10-01 · Qingyuan Liu, Jia-Chen Gu, Yunzhi Yao, Hong Wang 외 arxiv

Large language models (LLMs) require constant updates to remain aligned with evolving real-world knowledge. Model editing offers a lightweight alternative to retraining, but sequential editing often destabilizes represen…

knowledge editing