EchoEdit: Consistent Multi-Hop Question Answering via Ripple Control in Knowledge Editing

Knowledge editing aims to update specific knowledge in Large Language Models (LLMs) without retraining the entire model. However, existing methods generally struggle to manage the ripple effects of knowledge updates, particularly in multi-hop reasoning tasks, where conflicts between old and new information often lead to shifts in reasoning chains and degraded consistency. To address this issue, a ripple-aware knowledge editing framework, namely EchoEdit, is proposed. EchoEdit introduces the RippleGraph to explicitly model potentially affected knowledge regions and employs a RippleRule generator to dynamically produce diffusion rules, precisely constraining knowledge propagation. Furthermore, we distill a Chain-of-Thought (CoT) planner from an external teacher model, which decouples complex reasoning chain planning into RippleGraph-guided reasoning, thereby alleviating the reasoning burden on low-resource LLMs in multi-hop tasks. Experimental results on the MQuAKE and RIPPLEEDITS multi-hop reasoning benchmarks demonstrate that EchoEdit significantly outperforms existing mainstream methods, effectively enhancing post-edit reasoning consistency and generalization capabilities.

Authors

• Jinwei Shi State Key Laboratory for Novel Software Technology, Nanjing University
• Wenxuan Huang
• Yu Xing State Key Laboratory for Novel Software Technology, Nanjing University
• Yunhui Liu State Key Laboratory for Novel Software Technology, Nanjing University
• Tao Zheng
• Bin Chong National Engineering Laboratory for Big Data Analysis and Applications, Peking University
• Tieke He State Key Laboratory for Novel Software Technology, Nanjing University

Keywords

No keywords are indexed for this paper.