paper-with-me

Papers

Consistency-Aware Parameter-Preserving Knowledge Editing Framework for Multi-Hop Question Answering

2025-09-23 · Lingwen Deng, Yifei Han, Shijie Li, Yue Du, Bin Li arxiv

Parameter-Preserving Knowledge Editing (PPKE) enables updating models with new information without retraining or parameter adjustment. Recent PPKE approaches used knowledge graphs (KG) to extend knowledge editing (KE) capabilities to multi-hop question answering (MHQA). However, these methods often lack consistency, leading to knowledge contamination, unstable updates, and retrieval behaviors that are misaligned with the intended edits. Such inconsistencies undermine the reliability of PPKE in multi-hop reasoning. We present CAPE-KG, Consistency-Aware Parameter-Preserving Editing with Knowledge Graphs, a novel consistency-aware framework for PPKE on MHQA. CAPE-KG ensures KG construction, update, and retrieval are always aligned with the requirements of the MHQA task, maintaining coherent reasoning over both unedited and edited knowledge. Extensive experiments on the MQuAKE benchmark show accuracy improvements in PPKE performance for MHQA, demonstrating the effectiveness of addressing consistency in PPKE.

📄 PDF Abstract BibTeX arXiv:2509.18655

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-hop Question Answeringknowledge editingKnowledge Graphs

Similar Papers 제목 키워드 기반

Target-aware Image Editing via Cycle-consistent Constraints

2025-10-23 · Yanghao Wang, Zhen Wang, Long Chen arxiv

Recent pre-trained text-to-image flow models have enabled remarkable progress in text-based image editing. Mainstream approaches adopt a corruption-then-restoration paradigm, where the source image is first corrupted int…

Text-based Image EditingImage Reconstruction

ChainEdit: Propagating Ripple Effects in LLM Knowledge Editing through Logical Rule-Guided Chains

2025-07-11 · Zilu Dong, Xiangqing Shen, Zinong Yang, Rui Xia arxiv

Current knowledge editing methods for large language models (LLMs) struggle to maintain logical consistency when propagating ripple effects to associated facts. We propose ChainEdit, a framework that synergizes knowledge…

knowledge editingLogical Reasoning

Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems

2026-06-16 · Xinru Liu, Xianglong Zhang, Di Cai, Zhumin Chen 외 arxiv

Injecting malicious knowledge into retrieval-augmented generation (RAG) systems can manipulate retrieved evidence and mislead downstream generation, posing a serious security threat for AI applications. Existing RAG inje…

Consistency-Aware Editing for Entity-level Unlearning in Language Models

2025-12-19 · Xiaoqi Han, Víctor Gutiérrez-Basulto, Ru Li, Xiaoli Li 외 arxiv

Large language models (LLMs) risk retaining sensitive, copyrighted, or harmful information from their training data. Entity-level unlearning addresses this issue by removing all knowledge of a specific entity while prese…

Efficient Few-shot Identity Preserving Attribute Editing for 3D-aware Deep Generative Models

2025-10-21 · Vishal Vinod arxiv

Identity preserving editing of faces is a generative task that enables modifying the illumination, adding/removing eyeglasses, face aging, editing hairstyles, modifying expression etc., while preserving the identity of t…