Language Model Editing

Follow this topic Ask about this topic

Language model editing studies how to make targeted changes to a model’s stored knowledge, behavior, or generated text without retraining it from scratch. Common approaches locate relevant layers, neurons, or representations and apply low-rank, sparse, or null-space-constrained updates; others use activation steering, external retrieval, or modular memories for reversible and repeated edits. Methods are tested for edit success, generalization to paraphrases and related queries, locality on unrelated inputs, and retention of capabilities on benchmarks such as CounterFact and ZsRE. The central tension is that edits that generalize or accumulate at scale can interfere with existing knowledge and reasoning, while retrieval and other alternatives may preserve the base model more reliably.

Latest papers

77 papers12 papers in the last four weeks, up 33% on the four weeks before. 0.1% of all new papers.

Beyond Update Counts: A Control Map for Evaluating Test-Time Model Updates
Oct 26, 2026Zehao Zhao, Shangjian Yin, Rui Liu +6LLM Evaluation Inference-Time Adaptation of Language Models
Meta AI
DynEdit: Dynamic Entropy-Guided Sequential Editing for Large Language Models
Oct 26, 2026Jinhu Fu, Yan Bai, Yihang Lou +4Knowledge Editing Language Model Editing
Beijing University of Posts and Telecommunications · Peking University · AMAP, Alibaba Group +1
SEDATE: Do Large Language Models Share an Aggression Circuit Across Languages?
Oct 24, 2026Sagnik Basu, Sayan Das, Somnath Banerjee +1LLM Safety Language Model Editing
Indian Institute of Technology Kharagpur · Singapore Institute of Technology
FisherEdit: Fisher Information Guided Knowledge Editing for Large Language Models
Oct 19, 2026Yizhou Yang, Jiahong Fu, Zhiwu Wang +6Knowledge Editing Language Model Editing
Xi’an Jiaotong University · Zhejiang University · City University of Hong Kong +2
Causal Edit Serialization
Oct 16, 2026Louis RobinsonPointer Networks Language Model Editing
Independent Researcher
SAFETYEDIT: Sparse Internal Targets with Prompt-Wide Control for LLM Jailbreak Backdoors
Oct 15, 2026Yutong Ke, Yansu Wang, Zeyu Zhang +3LLM Backdoor Attacks Language Model Editing
Duke Kunshan University · Xi’an Jiaotong-Liverpool University · Wuhan University
From Spectral Saliency to Finite Deletion: Evaluating Selective Language Model Edits
Oct 13, 2026Ibne Farabi Shihab, Joyanta Jyoti MondalLanguage Model Editing LLM Pruning
Department of Computer and Information Sciences, University of Delaware, USA
Engram Injection: A Study of Temporal Validity in Parametric Language-Model Memory
Oct 11, 2026Sam Siavoshian, Omar Ramadan, Amir K. Saeed +2Temporal Reasoning in Language Models Persistent Memory for Language Models
Generalizable Model Editing Could Be More Than Direct Generalization
Oct 11, 2026Xiaotian Ye, Chunyao Yang, Xiaohan Wang +4Model Editing Language Model Editing
University of Cambridge · NLPR, MAIS, Institute of Automation, Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences, University of the Chinese Academy of Sciences +3
LadderEdit: Edit-Level Residual Compression for Memory-Efficient Lifelong Editing of LLMs
Oct 8, 2026Xiaobing Yu, Peijie Qiu, Jin Yang +5Language Model Editing Memory-Efficient Fine-Tuning
Yale University · Washington University in St. Louis · Icahn School of Medicine at Mount Sinai +1
FedAlphaEdit: Null-Space-Aligned Merging for Collaborative Knowledge Editing
Oct 8, 2026Sota Sugawara, Yukihiko OkadaKnowledge Editing Language Model Editing
Graduate School of Science and Technology, University of Tsukuba, Tsukuba, Japan · Center for Artificial Intelligence Research, Tsukuba Institute for Advanced Research, University of Tsukuba, Tsukuba, Japan · Institute of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan
HeadEdit: Calibrating Language Model Behavior Through the Frozen Unembedding Matrix
Oct 1, 2026Zirui He, Haiyan Zhao, Jingyu Hu +5Language Model Steering Language Model Calibration
New Jersey Institute of Technology · University of Bristol · Kuaishou Technology +1
How Should Diffusion Language Models Edit Code?
Sep 29, 2026Xijia Tao, Ziru Liu, Shansan Gong +7Masked Diffusion Models Language Model Editing
The University of Hong Kong · Huawei Technologies Ltd. · City University of Hong Kong +1
Generalizable Lifelong Model Editing via Preference Optimization
Sep 29, 2026Dahyun Jung, Suhyune Son, Heuiseok LimContinual Learning for LLMs Continual Learning
Department of Computer Science and Engineering, Korea University
ManiEdit: Sequential Unstructured Knowledge Editing for Language Models from a Manifold Perspective
Sep 27, 2026Rui Liu, Chenheng Zhang, Haoxuan Li +1Knowledge Editing Continual Learning for LLMs
State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · Institute for Artificial Intelligence, Peking University
From Latents to Wires: Surgical Post-Editing on Large Language Models
Sep 26, 2026Jiankai Jin, Xiangzheng Zhang, Zhao Liu +4Language Model Editing LLM Unlearning
AI Security Lab
ALOE: Semantically Addressed Low-Rank Operators for Knowledge Editing
Sep 24, 2026Zeyan Li, Hu Xu, Jianfeng XuFactual Knowledge in Language Models Language Model Editing
Shanghai Jiao Tong University
The information geometry of large language models is shared, learned, and controllable
Sep 10, 2026Dario PicozziInformation Geometry Language Model Steering
Department of Physics and Astronomy, University College London (UCL), Gower Street, London WC1E 6BT, United Kingdom · London Centre for Nanotechnology, 19 Gordon St, London WC1H 0AH, United Kingdom
Training-Free Task Vectors for LLM Behavioral Control
Sep 8, 2026Gabriel J. Perin, Lucas Boscaini, André Araujo +1Task Vectors AI Control
University of São Paulo · Google · Google DeepMind
MM-SVGEdit: A Multimodal-Driven SVG Editing for UI Design
Sep 5, 2026Shibo Yang, Yuqing Gao, Zipeng LiuImage Editing Language Model Editing
Beihang University Beijing, China
When Models Edit Too Much: On the Fidelity of Minimal Code Edits
Sep 3, 2026Tongyao Zhu, Wei Hern Lim, Min-Yen KanAutomated Program Repair Language Model Editing
National University of Singapore
SCoNE: Selective Context-aware Neuron Editing for Robust Retrieval-Augmented Generation
Sep 1, 2026Chaewon Kim, Seo Yeon ParkRetrieval-Augmented Generation Retrieval Robustness
Hanyang University
Sequential knowledge editing breaks a model's ability to tell good evidence from bad, without costing it accuracy
Aug 31, 2026Atul AnandKnowledge Editing Language Model Editing
AI Writers Have a Consistent Stylometric Footprint, but AI Editors Do Not
Aug 28, 2026Zhengyang Shan, Yukyung Lee, Sophie HaoAI-Generated Text Detection Language Model Fingerprinting
Boston University
KLOD: Locality-Preserving Knowledge Editing via Non-Target Distribution Preservation
Aug 28, 2026Hojun Jeong, Gyunyeop Kim, Sangwoo KangKnowledge Editing Language Model Editing
Department of Computing, Gachon University
PersonaEdit: Representative Sample Selection for Personalized Model Editing
Aug 28, 2026You-Mei Huang, Chung-Chi Chen, An-Zi YenLLM Personalization Model Editing
Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan · Human-Agent Ally Lab (HAA Lab), National Institute of Informatics (NII), Japan
Towards Reliable, Generalizable, and Specific In-Context Knowledge Editing via Multi-Objective Reinforcement Learning
Aug 25, 2026Xuzhong Wang, Maiqi Jiang, Tejal Nair +3Knowledge Editing Language Model Editing
College of William and Mary · Tribhuvan University
ACE: A Self-Correcting Agentic Canvas Editor for Multi-Slide Presentation Automation
Aug 25, 2026JooYoung Jang, Taegyeong Lee, Jihyeon Park +1Scene Graphs Language Model Editing
Seoul National University · Miridih
PatchWrite: One Line, Not One Section -- Compile-Gated, Validity-Preserving Editing for AI-Drafted Manuscripts
Aug 24, 2026Weiwei YangScientific Workflow Automation Language Model Editing
Solus
Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing
Aug 12, 2026Tianci Liu, Zihan Dong, Tianchun Li +8Knowledge Editing Self-Distillation
University of Tennessee · 2Rutgers University · 3Purdue University +1

Oct 26, 2026J/K move · Enter open · S save

Beyond Update Counts: A Control Map for Evaluating Test-Time Model Updates

Zehao Zhao, Shangjian Yin, Rui Liu, Chongyang Bai+5

Meta AI

LLM Evaluation Inference-Time Adaptation of Language Models Language Model Editing

Open paper AskPDF arXiv

Test-time updating lets a language model change persistent state after training---such as model weights, adapter parameters, or a memory module---before or while answering queries. Existing evaluations often compare systems using update count or frequency and performance measured immediately afterward. These summaries omit what is updated, where, when, and in what order. The same total can therefore hide an important difference: one system may answer after one update while another answers after two. We introduce the Control Map, an evaluation framework that records the committed updates preceding each scored answer and separately evaluates behavioral changes, immediate learning (acquisition), later recall (retention), preservation of unrelated behavior (locality), and performance in new settings. We prove when counts alone determine final state and show, under stated assumptions, how differences between pre-answer histories limit differences in average scores. Using ControlMap, our experiments reveal three insights. First, update scheduling matters: at a 760M-parameter checkpoint, 24 schedules with the same update count yield 19.7%--34.2% accuracy. Second, learning an edit does not guarantee that it lasts or remains contained: all six selected CounterFact LoRA settings learn the new information, while ROME retains edits at all 13 operating points but fails locality at each. Third, no editor performs best consistently across models, benchmarks, and tests. Evaluations should therefore report update histories and assess acquisition, retention, and locality separately.