EMNLP Findings2025
Knowledge Graph-Driven Memory Editing with Directional Interventions
Jinhu Fu, Kun Wang, Chongye Guo, Junfeng Fang, Wentao Zhang, Sen Su
Abstract
Large Language Models (LLMs) have revolutionized language processing and understanding, yet their performance is hampered by inaccuracies and outdated information. Model editing techniques offer a solution but face two key challenges: (I) Most methods inject knowledge by constructing rigid loss, which leads to poor compatibility when dealing with higherorder multi-hop problems. (II) Locate-thenedit vein, by altering pre-trained parameters, inevitably affect normal knowledge and even face the catastrophic forgetting. In this paper, we introduce KGMET, a framework that constructs knowledge graphs using available information to guide the direction of knowledge editing, enabling consistent, aligned, and stable information during large-scale editing scenario. Furthermore, KGMET goes beyond this by employing orthogonal constraints to block the interference of irrelevant information, ensuring the updates are both controllable and generalizable. Experiments on Multi-Conterfact, ZsRE, and MQuAKE datasets using Llama-3-8B, GPT-J-6B, and GPT-2-XL models showcase improvements over state-of-the-art methods, with ↑ 5% -17% in multi-hop tasks while remaining generalizable (at least ↑ 20% in fluency). Our code is available on GitHub 1 .
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors cites LoRA: Low-Rank Adaptation of Large Language Models
- TruthfulQA: Measuring How Models Mimic Human Falsehoods cites Measuring Massive Multitask Language Understanding
- Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting cites LoRA: Low-Rank Adaptation of Large Language Models
- Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting cites Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection
- Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting cites Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
- Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting cites Measuring Massive Multitask Language Understanding
- Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting cites Investigating Gender Bias in Language Models Using Causal Mediation Analysis
Cited by top-tier papers2
- Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace ProjectionJinhu Fu, Yihang Lou, Qingyi Si, Shudong Zhang et al.CVPR 2026 · 3 citations
- Learning to Edit Knowledge via Instruction-based Chain-of-Thought PromptingJinhu Fu, Yan Bai, Longzhu He, Yihang Lou et al.ACL 2026 · 1 citation
Builds on21
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- Measuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, Andy Zou et al.ICLR 2021 · 7,905 citations
- TruthfulQA: Measuring How Models Mimic Human FalsehoodsStephanie Lin, Jacob Hilton, Owain EvansACL 2022 · 3,228 citations
- Investigating Gender Bias in Language Models Using Causal Mediation AnalysisJesse Vig, Sebastian Gehrmann, Yonatan Belinkov, Sharon Qian et al.NeurIPS 2020 · 851 citations
- Aging with GRACE: Lifelong Model Editing with Discrete Key-Value AdaptorsTom Hartvigsen, Swami Sankaranarayanan, Hamid Palangi, Yoon Kim et al.NeurIPS 2023 · 349 citations
Related papers
- Knowledge Graph Enhanced Large Language Model EditingMengqi Zhang, Xiaotian Ye, Qiang Liu, Pengjie Ren et al.EMNLP 2024 · 5 citations
- Resolving UnderEdit & OverEdit with Iterative & Neighbor-Assisted Model EditingBhiman Kumar Baghel, Emma Jordan, Zheyuan Ryan Shi, Xiang Lorraine LiEMNLP Findings 2025 · 1 citation
- LLM-Based Multi-Hop Question Answering with Knowledge Graph Integration in Evolving EnvironmentsRuirui Chen, Weifeng Jiang, Chengwei Qin, Ishaan Singh Rawal et al.EMNLP Findings 2024 · 12 citations
- EAMET: Robust Massive Model Editing via Embedding Alignment OptimizationYanbo Dai, Zhenlan Ji, Zongjie Li, Shuai WangICLR 2026
- Forget for Get: A Lightweight Two-phase Gradient Method for Knowledge Editing in Large Language ModelsYanhong Li, Min Yang, Xiping Hu, Chengming LiEMNLP Findings 2025
