Papers with knowledge editing
Knowledge Control for Responsible Generative AI: Bridging Academia, Industry, and Society (2026.acl-tutorials)
Copied to clipboard
Zheyuan Liu, Yixin Wan, Kai-Wei Chang, Meng Jiang, Jieyu Zhao, Nouha Dziri, Yuning Mao, Jia-Chen Gu, Jindong Gu
| Challenge: | This tutorial introduces the foundations of post-training knowledge control and showcases recent frontier methods. |
| Approach: | This tutorial introduces the foundations of post-training knowledge control and showcases recent frontier methods. |
| Outcome: | This tutorial introduces the foundations of post-training knowledge control and showcases recent frontier methods . key motivations and failure modes, harmful generation and stereotype reinforcement, are addressed . core methods such as machine unlearning, knowledge editing, and inference-time interventions are also included . |
EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models (2024.acl-demos)
Copied to clipboard
Peng Wang, Ningyu Zhang, Bozhong Tian, Zekun Xi, Yunzhi Yao, Ziwen Xu, Mengru Wang, Shengyu Mao, Xiaohan Wang, Siyuan Cheng, Kangwei Liu, Yuansheng Ni, Guozhou Zheng, Huajun Chen
| Challenge: | Large Language Models (LLMs) suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data. |
| Approach: | They propose an easy-to-use knowledge editing framework for Large Language Models that allows users to easily edit updated knowledge and adjust undesired behavior while minimizing the impact on unrelated inputs. |
| Outcome: | The proposed framework surpasses traditional fine-tuning in terms of reliability and generalization. |
Aligning Language Models with Real-time Knowledge Editing (2026.acl-long)
Copied to clipboard
| Challenge: | Mainstream knowledge editing methods are static and fail to keep pace with the evolving real-world knowledge. |
| Approach: | They propose a new paradigm for knowledge editing that integrates edit augmentation and self-adaptive post-alignment inference into CRAFT to improve edit success. |
| Outcome: | The proposed method shows significant performance gain on CRAFT and traditional datasets compared to existing methods. |
Retrieval-Augmented Multilingual Knowledge Editing (2024.acl-long)
Copied to clipboard
| Challenge: | Knowledge editing (KE) is an effective and economical alternative to inject new knowledge or to fix factual errors in Large Language Models (LLMs). |
| Approach: | They propose a multilingual knowledge editing method that can be used to update knowledge in LLMs by concatenating new knowledge retrieved from a knowledge base with users’ prompts before querying an LLM. |
| Outcome: | The proposed method outperforms baseline knowledge editing methods by a significant margin and is scalable to real-word application scenarios. |
Model Merging for Knowledge Editing (2025.acl-industry)
Copied to clipboard
Zichuan Fu, Xian Wu, Guojing Li, Yingying Zhang, Yefeng Zheng, Tianshi Ming, Yejing Wang, Wanyu Wang, Xiangyu Zhao
| Challenge: | Existing knowledge editing approaches struggle with sequential editing scenarios and harm the general capabilities of the model. |
| Approach: | They propose a framework that combines robust supervised fine-tuning and model merging for knowledge editing to combine supervised and supervised learning. |
| Outcome: | The proposed approach outperforms existing methods in sequential editing while preserving the original performance of the model. |
Persuasion Tokens for Editing Factual Knowledge in LLMs (2026.eacl-short)
Copied to clipboard
| Challenge: | In-context knowledge editing (IKE) relies on fact-specific demonstrations which consume significant context window space. |
| Approach: | They introduce persuasion tokens (P-Tokens) which replicate the effect of IKE demonstrations and allow efficient knowledge editing without requiring fact-specific demonstrations. |
| Outcome: | The proposed tokens perform comparable to and often exceed IKE on two editing datasets and three LLMs and increase the number of tokens increases performance. |
Editing Conceptual Knowledge for Large Language Models (2024.findings-emnlp)
Copied to clipboard
Xiaohan Wang, Shengyu Mao, Shumin Deng, Yunzhi Yao, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen, Ningyu Zhang
| Challenge: | Existing knowledge editing methods can modify concept-level definitions, but they can distort instantial knowledge in LLMs, leading to poor performance. |
| Approach: | They construct a benchmark dataset ConceptEdit and establish new metrics for evaluation to investigate the editing capability of LLMs. |
| Outcome: | The proposed methods can modify concept definitions but can distort instantial knowledge in LLMs, leading to poor performance. |
RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models have strong generalizability, but fine-tuning involves updating all parameters, rendering full fine-uning resource-intensive. |
| Approach: | They propose a parameter-efficient fine-tuning method that updates all pre-trained parameters during inference. |
| Outcome: | The proposed method outperforms baseline methods on five benchmarks across 20 datasets. |
Efficient Knowledge Editing via Minimal Precomputation (2025.acl-short)
Copied to clipboard
| Challenge: | Knowledge editing methods like MEMIT require a one-time but significant computational cost. |
| Approach: | They propose to pre-compute 44 million hidden vectors per edited layer . authors show that this precomputation step is unnecessary . |
| Outcome: | The proposed methods can be performed by pre-computing a small portion of 44 million hidden vectors. |
Detoxifying Large Language Models via Knowledge Editing (2024.acl-long)
Copied to clipboard
Mengru Wang, Ningyu Zhang, Ziwen Xu, Zekun Xi, Shumin Deng, Yunzhi Yao, Qishen Zhang, Linyi Yang, Jindong Wang, Huajun Chen
| Challenge: | Existing methods to detoxify Large Language Models (LLMs) are limiting, but knowledge editing can be effective. |
| Approach: | They propose a baseline method to detoxify Large Language Models (LLMs) they propose supervised fine-tuning and reinforcement learning from human feedback (RLHF) |
| Outcome: | The proposed method reduces toxicity of large language models with one instance of tuning . it reduces the toxicity, while minimizing the toxins, the authors show . |
Neuron-Level Knowledge Attribution in Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for attribution of knowledge in large language models struggle to operate at neuron level due to computational constraints. |
| Approach: | They propose a static method for pinpointing significant neurons using three metrics . they also propose identifying "query neurons" which activate these "value neurons" |
| Outcome: | The proposed method shows superior performance across three metrics compared to seven other methods . it analyzes six types of knowledge across attention and feed-forward network layers . |
WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge editing methods focus on single editing, failing to meet the requirements for lifelong editing. |
| Approach: | They propose an approach that selects editing layer based on the pattern matching degree of editing knowledge across different layers in language models. |
| Outcome: | The proposed method improves on GPT2-XL and GPT-J in lifelong editing compared to state-of-the-art methods . |
Learning to Edit: Aligning LLMs with Knowledge Editing (2024.acl-long)
Copied to clipboard
Yuxin Jiang, Yufei Wang, Chuhan Wu, Wanjun Zhong, Xingshan Zeng, Jiahui Gao, Liangyou Li, Xin Jiang, Lifeng Shang, Ruiming Tang, Qun Liu, Wei Wang
| Challenge: | Existing knowledge editing techniques rely on memorizing updated knowledge, impeding LLMs from effectively combining the new knowledge with their inherent knowledge when answering questions. |
| Approach: | They propose a Learning to Edit framework that equips LLMs with the ability to apply updated knowledge to input questions through a two-phase process . |
| Outcome: | The proposed framework outperforms existing methods in knowledge editing tasks and compares it with four benchmarks and two LLM architectures. |
Knowledge Graph-Driven Memory Editing with Directional Interventions (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are hampered by inaccuracies and outdated information. |
| Approach: | They propose a framework that constructs knowledge graphs using available information to guide the direction of knowledge editing. |
| Outcome: | The proposed framework allows consistent, aligned, and stable information during large-scale editing scenarios. |
CLICKER: Cross-Lingual Knowledge Editing via In-Context Learning with Adaptive Stepwise Reasoning (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing knowledge editing methods are static and fail to propagate edits across languages. |
| Approach: | They propose a KE method that dynamically retrieves only knowledge relevant to a given query and edits it to maintain cross-lingual consistency. |
| Outcome: | The proposed method outperforms static KE methods on a multilingual dataset with semantically similar but irrelevant prompts. |
Tracking the Limits of Knowledge Propagation: How LLMs Fail at Multi-Step Reasoning with Conflicting Knowledge (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing benchmarks for analyzing the performance of Large Language Models (LLMs) focus on single knowledge updates and fact recall, but do not consider how these updates affect downstream reasoning. |
| Approach: | They propose a benchmark to study how LLMs propagate new knowledge when it conflicts with the model's parametric knowledge. |
| Outcome: | The proposed benchmark compared models with no updated facts to show that the new methods worsen performance and improve reasoning performance. |
Editing the Moving World: Model Editing for Video LLMs (2026.acl-long)
Copied to clipboard
Qian Zhang, Xinye Li, Xiaokai Wu, Junhao Xu, Zhanyue Qin, Qingbin Liu, Junxian Cai, Xi Chen, Bolin Zhang, Zhiying Tu, Dianhui Chu, Xiaoyan Yu, Dianbo Sui
| Challenge: | Existing models for knowledge editing focus on knowledge-level or static visual domains, overlooking dynamic semantics. |
| Approach: | They propose a benchmark for modeling large language models using six representative models . they analyze the strengths and limitations of existing models and identify new directions . |
| Outcome: | The proposed benchmark extends existing models from static modalities to dynamic video scenarios. |
MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing (2024.findings-acl)
Copied to clipboard
Jiaqi Li, Miaozeng Du, Chuanyi Zhang, Yongrui Chen, Nan Hu, Guilin Qi, Haiyun Jiang, Siyuan Cheng, Bozhong Tian
| Challenge: | Current benchmarks focus on coarse-grained knowledge, leaving the intricacies of fine-grounded knowledge unexplored. |
| Approach: | They propose a benchmark and dataset specifically designed for FG multimodal entity knowledge editing. |
| Outcome: | The proposed benchmark underscoring the complexity of FG knowledge editing in MLLMs. |
RippleCOT: Amplifying Ripple Effect of Knowledge Editing in Language Models via Chain-of-Thought In-Context Learning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | et al., 2022: ripple effect challenges knowledge editing for large language models. |
| Approach: | They propose a method to improve the accuracy of large language models by integrating Chain-of-Thought reasoning into the ICL editing approach. |
| Outcome: | RIPPLE-COT outperforms the state-of-the-art on the ripple effect, with gains ranging from 7.8% to 87.1%. |
Forget for Get: A Lightweight Two-phase Gradient Method for Knowledge Editing in Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing knowledge editing methodologies often encounter parameter conflict during knowledge overwriting and excessive computational overhead. |
| Approach: | They propose a method that erases outdated knowledge and inserts new knowledge at the location that corresponds to the target knowledge. |
| Outcome: | The proposed method achieves more effective knowledge editing at a lower cost compared to previous methods across various base models. |
PokeMQA: Programmable knowledge editing for Multi-hop Question Answering (2024.acl-long)
Copied to clipboard
| Challenge: | Multi-hop question answering (MQA) is one of the challenging tasks to evaluate machine’s comprehension and reasoning abilities, where large language models (LLMs) have widely achieved the human-comparable performance. |
| Approach: | They propose a framework to edit multi-hop question models to update model with up-to-date facts while avoiding expensive re-training or fine-tuning. |
| Outcome: | The proposed framework outperforms all competitors in multi-hop question answering tasks and consistently produces reliable reasoning process. |
BABELEDITS: A Benchmark and a Modular Approach for Robust Cross-lingual Knowledge Editing of Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for cross-lingual knowledge editing are limited in their effectiveness and robustness. |
| Approach: | They propose a new CKE benchmark that accounts for the rich variety of entity aliases within and across languages. |
| Outcome: | The proposed method is more effective than state-of-the-art methods and robust against model collapse when subjected to multiple edits. |
DistillMIKE: Editing Distillation of Massive In-Context Knowledge Editing in Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | In-context knowledge editing has shown respectable abilities on knowledge editing in terms of generalization and specificity. |
| Approach: | They propose a novel extension of in-context knowledge editing (IKE) that allows for massive edits to be injected into large language models. |
| Outcome: | The proposed method shows state-of-the-art perfomrances and comparable performance with MIKE. |
KoLEG: On-the-Fly Korean Legal Knowledge Editing with Continuous Retrieval (2025.findings-emnlp)
Copied to clipboard
Jaehyung Seo, Dahyun Jung, Jaewook Lee, Yongchan Chun, Dongjun Kim, Hwijung Ryu, Donghoon Shin, Heuiseok Lim
| Challenge: | a recent study shows that Korean legal knowledge is subject to frequent temporal updates driven by societal needs and government policies. |
| Approach: | They propose a Korean Legal knowledge editing framework enhanced with continuous retrieval . they employ an Editing-Aware Learning Strategy and a LawEdit Retriever . |
| Outcome: | a new framework outperforms existing methods for updating legal knowledge in Korean . it maintains robust performance in sequential editing and is qualitatively validated by legal experts. |
RAG or Learning? Understanding the Limits of LLM Adaptation under Continuous Knowledge Drift in the Real World (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to update or supplement large language models struggle under continuous knowledge drift. |
| Approach: | They propose a dynamic event benchmark and time-aware retrieval baseline that captures how knowledge evolves over time. |
| Outcome: | The proposed method enables systematic evaluation of model adaptation under continuous knowledge drift. |
Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Knowledge editing is a promising technique for updating factual knowledge in large language models (LLMs) but studies have identified side effects such as knowledge distortion and the deterioration of general abilities that have emerged after editing. |
| Approach: | They propose to evaluate the side effects of knowledge editing in large language models using metrics and benchmarks. |
| Outcome: | The results of the study highlight the limitations of current knowledge editing methods and outline potential research directions. |
Cross-Lingual Knowledge Editing in Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Knowledge editing is a promising technique to adapt large language models to new knowledge without retraining from scratch. |
| Approach: | They propose to use a multilingual dataset to translate a large-scale cross-lingual synthetic dataset from English to Chinese and then to evaluate their performance in Chinese. |
| Outcome: | The proposed method can change model performance on several special cases without retraining from scratch. |
ChainEdit: Propagating Ripple Effects in LLM Knowledge Editing through Logical Rule-Guided Chains (2025.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge editing methods for large language models struggle to maintain logical consistency when propagating ripple effects to associated facts. |
| Approach: | They propose a framework that synergizes knowledge graph-derived logical rules with LLM logical reasoning capabilities to enable systematic chain updates. |
| Outcome: | The proposed framework improves logical generalization and specificity while maintaining reliability and specificness. |
One for All: Update Parameterized Knowledge Across Multiple Models with Once Edit (2025.acl-long)
Copied to clipboard
Weitao Ma, Xiyuan Du, Xiaocheng Feng, Lei Huang, Yichong Huang, Huiyi Zhang, Xiaoliang Yang, Baohang Li, Xiachong Feng, Ting Liu, Bing Qin
| Challenge: | Existing methods for modifying large language models focus on individual models, resulting in errors and hallucinations. |
| Approach: | They propose an ensemble-based approach that employs a plug-in model as the editing module and a dynamic weight mechanism to enhance its effectiveness. |
| Outcome: | The proposed approach outperforms existing methods while achieving superior editing efficiency. |
Commonsense Knowledge Editing Based on Free-Text in LLMs (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge editing methods focus on editing triple-based facts such as entity-relation pairs and events (multiple triplets). |
| Approach: | They propose a Knowledge Localization for Free-Text method which uses a Dynamics-aware Module to locate the parameter positions corresponding to commonsense knowledge and a knowledge editing module to update knowledge. |
| Outcome: | The proposed method exploits the potential of the MLP and Attention layers and edits commonsense knowledge based on free-text. |
Decoding by Contrasting Knowledge: Enhancing Large Language Model Confidence on Edited Facts (2025.acl-long)
Copied to clipboard
| Challenge: | In-context knowledge editing (ICE) is currently the most effective method for knowledge editing, but it is constrained by the black-box modeling of LLMs and lacks interpretability. |
| Approach: | They propose a method to decode new knowledge by comparing logits with unedited knowledge to improve the accuracy of LLMs. |
| Outcome: | The proposed method improves the performance of LLaMA3-8B-instruct on MQuAKE by up to 219%. |
AKEW: Assessing Knowledge Editing in the Wild (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent Large Language Models (LLMs) have revolutionized the NLP field but their knowledge could become incorrect or outdated over time. |
| Approach: | They propose a new practical benchmark for knowledge editing that covers three editing settings of knowledge updates: structured facts, unstructured texts as facts, and extracted triplets. |
| Outcome: | The proposed method covers structured facts, unstructured texts as facts, and extracted triplets. |
LLM-Based Multi-Hop Question Answering with Knowledge Graph Integration in Evolving Environments (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for knowledge editing in Large Language Models face difficulties with multi-hop questions that require accurate fact identification and sequential logical reasoning. |
| Approach: | They propose a method that merges explicit knowledge representations of Knowledge Graphs with the linguistic flexibility of Large Language Models to convert free-form language into structured queries and fact triples. |
| Outcome: | The proposed method significantly surpasses state-of-the-art knowledge editing methods in the multi-hop question answering benchmark, MQuAKE. |
Dynamic Retriever for In-Context Knowledge Editing via Policy Optimization (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models excel at factual recall yet propagate stale or incorrect knowledge. |
| Approach: | They propose a framework that allows users to rank demonstrations by editing reward . it uses a *learnable threshold* to prune low-value examples, reducing edit success by 17.1% . |
| Outcome: | The proposed framework improves edit success by 17.1% and reduces latency by 41.6% on the CounterFact benchmark. |
Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for knowledge editing fail to work in multi-hop question answering due to 'edit skipping' edit skipping occurs due to the mismatch between the granularity of LLMs in problem-solving and the facts in the edited memory. |
| Approach: | They propose a retrieval-augmented generation-based method that edits knowledge without modifying parameters without retraining LLMs. |
| Outcome: | The proposed method outperforms state-of-the-art methods for KE in multi-hop question answering. |
MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks for knowledge editing in multimodal large language models focus on limited scenarios due to the lack of rigorous definition of multimodal knowledge. |
| Approach: | They propose a decomposed definition of multimodal knowledge and a benchmark to evaluate it. |
| Outcome: | The proposed method reveals that it is difficult to define multimodal knowledge editing in LLMs. |
Neuron Empirical Gradient: Discovering and Quantifying Neurons’ Global Linear Controllability (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies have shown that feed-forward neurons in pre-trained language models (PLMs) can encode factual knowledge, but current methods are costly and lack the link between activations and outputs. |
| Approach: | They propose to compute a global linear relationship between neuron activations and outputs using a knowledge probing dataset. |
| Outcome: | The proposed method exploits the neural empirical gradient to capture changes in neuron activations and model outputs. |
Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting (2026.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge editing methods focus on structured fact triples, overlooking diverse unstructured forms of factual information. |
| Approach: | They propose a method that allows LLMs to edit knowledge via **Chain of Thoughts** reasoning. |
| Outcome: | The proposed method achieves strong generalization across six diverse knowledge editing scenarios with a single round of training on three open-source language models. |
Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge editing approaches directly edit model context without isolating target knowledge from the reasoning path of model inference, resulting in unreliable and low-quality outputs, especially in multi-hop tasks. |
| Approach: | They propose a framework that separates model reasoning from knowledge editing and propose 'DecKER' that allows users to modify specific factual associations without retraining the entire model. |
| Outcome: | The proposed framework significantly improves multi-hop reasoning performance by mitigating knowledge conflicts and preserving reasoning integrity. |
Can We Edit LLMs for Long-Tail Biomedical Knowledge? (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing knowledge editing methods can enhance LLMs' performance on long-tail biomedical knowledge, but their performance on high-frequency popular knowledge remains inferior to that on high frequency popular knowledge. |
| Approach: | They conduct the first comprehensive study to investigate the effectiveness of knowledge editing methods for editing long-tail biomedical knowledge. |
| Outcome: | The proposed methods improve LLMs' performance on long-tail biomedical knowledge, but their performance on high-frequency popular knowledge remains inferior even after editing. |
Decoupled Reasoning with Implicit Fact Tokens (DRIFT): A Dual-Model Framework for Efficient Long-Context Inference (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing solutions to integrate extensive, dynamic knowledge into Large Language Models (LLMs) are constrained by finite context windows, retriever noise, or the risk of catastrophic forgetting. |
| Approach: | They propose a dual-model architecture that explicitly decouples knowledge extraction from the reasoning process by compressing document chunks into implicit fact tokens conditioned on the query. |
| Outcome: | The proposed architecture significantly outperforms strong baselines among comparably sized models on long-context tasks while maintaining inference accuracy. |