Model Editing

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 53

All topics

FORGE: Verification-Gated Behavioral Repair for Generative Language Models
Oct 4, 2026Hsin-Ling Hsu, Min-Yu Chen, Nai-Chia Chen +3Social Bias in Language Models LLM Safety
Department of Management Information Systems National Chengchi University Taipei, Taiwan
Operational Abstractions of Neural Network Concepts via Topological Representations
Oct 4, 2026Mathieu Pont, Christoph GarthDisentangled Representation Learning Model Editing
RPTU Kaiserslautern-Landau RPTU Kaiserslautern-Landau Kaiserslautern, Germany
Repurposing Obsolete Representations for Post-Deployment Adaptation
Oct 1, 2026Daniel Bethell, Charmaine Barker, Simos GerasimouModel Editing Machine Unlearning
Department of Computer Science, University of York, UK · Department of Elect. Eng., and Computer Science and Eng., Cyprus University of Technology, Cyprus
STAGE: Subspace-Targeted Affine Generative Erasure for Text-to-3D Models
Oct 1, 2026Karol Dziekan, Przemysław Spurek, Dawid Malarz3D Asset Generation Text-to-3D Generation
Jagiellonian University · IDEAS Research Institute
Platonic Task Arithmetic
Oct 1, 2026Junghwan Park, Woojin ChoVLM Adaptation Task Arithmetic
TelePIX
LLM Persona Unlearning
Sep 30, 2026Kemou Li, Zhuan Shi, Qizhou Wang +4Model Editing Persona-Conditioned Generation
State Key Laboratory of Internet of Things for Smart City, University of Macau · Mila – Québec AI Institute · McGill University +3
Imprint Reader: From Weight-Update Readout to Behavioral Intervention
Sep 28, 2026Guanxu Chen, Qihao Lin, Jing ShaoLLM Interpretability Neural Network Interpretability
Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University
Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration
Sep 14, 2026Aashiq Muhamed, Mona T. Diab, Virginia SmithAdversarial Attacks on LLMs LLM Safety
Carnegie Mellon University
Beyond Global Editing: Per-Instance Disentangled Subspaces for Training-Free Hallucination Mitigation in LVLMs
Aug 10, 2026Ali Cheraghian, Hamidreza Dastmalchi, Hamed Barzamini +4Large Vision-Language Models Model Editing
Macquarie University, Australia · Australian National University, Australia · York University, Canada +4
PRISM Edit: One Vector for All Temporal Answers
Jul 13, 2026Chen Huang, Qi Zheng, Ruiqin Zheng +2Temporal Reasoning in Language Models Model Editing
Tsinghua University · ByteDance
Evaluating and Understanding Model Editing for Medical Vision Language Models
Jul 6, 2026Guli Zhu, Chenwei Wu, Liyue ShenKnowledge Editing Medical VLMs
EECS, University of Michigan, Ann Arbor, MI 48105, USA
Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing
Jul 2, 2026Siyuan Li, Youyuan Zhang, Ruitong Liu +2Knowledge Editing Multimodal Large Language Models
Harbin Institute of Technology, Shenzhen, China · Peng Cheng Laboratory · Peking University +1
KnowledgeDebugger -- an Exploration Tool for Knowledge Localization and Editing in Transformers
Jul 1, 2026Eric Benz, Lennart Stöpler, Nikolai Bolik +1Knowledge Editing Transformer Interpretability
Heidelberg University
Revocable Learned State via Process Sidecars
Jun 29, 2026John SweeneyLLM Safety Alignment Task Arithmetic
Sideplane AI
Reproducibility Study of "AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models"
Jun 25, 2026Ananth K Suresh, Arya HariharanKnowledge Editing Model Editing
Independent
Orthogonal Representation Editing: Decoupling Semantic Entanglement in Batch Knowledge Editing of LLMs
Jun 21, 2026Wenhao Yu, Zhicong Lu, Bo Lv +4Knowledge Editing Model Editing
School of Computer Science and Technology, Tianjin University · Kexin Technology · University of Chinese Academy of Sciences +2
BIM-Edit: Benchmarking Large Language Models for IFC-Based Building Information Modeling
Jun 18, 2026Bharathi Kannan Nithyanantham, Clemens Kujat, Tobias Sesterhenn +5LLM Evaluation Building Information Modeling
University of Rostock · Clausthal University of Technology
LOKI: Memory-Free Null-Space Constrained Lifelong Knowledge Editing
Jun 18, 2026Masih Eskandar, Miquel Sirera Perelló, Stratis Ioannidis +1Knowledge Editing Continual Learning for LLMs
Department of Electrical and Computer Engineering Northeastern University Boston, MA, 02115
Repeated Shared Access Enables Grokking, but Edit Propagation Depends on an Addressable Memory
Jun 17, 2026Yanan NiuMemory-Augmented Neural Networks Knowledge Editing
Kuaishou Technology
User as Engram: Internalizing Per-User Memory as Local Parametric Edits
Jun 17, 2026Bojie LiKnowledge Editing LLM Personalization
Pine AI
When to Write and When to Suppress: Route-Specialized Dual Adapters for Memory-Assisted Knowledge Editing
Jun 12, 2026Baijia Zhang, Yining HuangKnowledge Editing Factual Knowledge in Language Models
Xinjiang University · Meta Emergence Laboratory
Reinforcement Learning for Neural Model Editing
Jun 11, 2026Shaivi MalikReinforcement Learning Model Editing
TimeROME-DLM: Temporal Causal Tracing and Low-Rank Inference-Time Knowledge Editing for Masked Diffusion Language Models
Jun 11, 2026Zhengtao Yao, Liuyang Song, Hongbo Zhang +4Knowledge Editing Masked Diffusion Models
University of Southern California, USA · Peking University, China · Stevens Institute of Technology, USA +1
LoMC: Localized Multidirectional Correction for Refusal Suppression in Routed Foundation Models
Jun 10, 2026Yan Hong, Kedong Xiu, Wei Li +6Mixture-of-Experts Language Models LLM Refusal Behavior
Ant Group · Zhejiang University · Shanghai Jiao Tong University
Can Editing 1 Neuron Fix Repetition Loops in LLMs?
Jun 9, 2026Aristotelis Lazaridis, Aman Sharma, Dylan Bates +3LLM Self-Correction Mechanistic Interpretability
Edgerunner AI
CRANE: Knowledge Editing for Reasoning MLLMs
Jun 8, 2026Han Huang, Hao Wang, Mengqi Zhang +3Knowledge Editing Knowledge Conflicts in Language Models
University of Chinese Academy of Sciences, Beijing 101408, China, and also with the New Laboratory of Pattern Recognition (NLPR), CASIA, Beijing 100045, China · Harbin Institute of Technology, Weihai 264209, China · School of Computer Science and Technology, Shandong University, Qingdao 266237, China
Knowledge Editing for Masked Diffusion Language Models
Jun 2, 2026Haewon Park, Yohan JoKnowledge Editing Masked Diffusion Models
Graduate School of Data Science, Seoul National University
Revisiting Ripple Effects in Knowledge Editing through Pressure-Aware Joint Neighborhood Optimization
Jun 1, 2026Haoben Huang, Shuxin Liu, Ou Wu +1Knowledge Editing Model Editing
Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, China · College of Information Engineering, Zhejiang University of Technology, Hangzhou, China
Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence
May 30, 2026Wanying Ren, Xin Song, Futing Wang +2Model Editing Language Model Editing
East China Normal University, Shanghai, China · Westlake University, Hangzhou, China · Nanyang Technological University, Singapore
Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs
May 30, 2026Xin Gao, Cheng Yang, Chufan Shi +1Knowledge Editing Unified Multimodal Models
University of California San Diego · University of Southern California

Oct 4, 2026, cs.CLJ/K move · Enter open · S save

FORGE: Verification-Gated Behavioral Repair for Generative Language Models

Hsin-Ling Hsu, Min-Yu Chen, Nai-Chia Chen, Yan-Ru Chen+2

Department of Management Information Systems National Chengchi University Taipei, Taiwan

Social Bias in Language Models LLM Safety Model Editing

Open paper AskPDF arXiv

Generative large language models (LLMs) inherit undesirable behaviors from pre-training, including demographic bias and toxic generation, that often emerge only after deployment and affect a small subset of inputs. A repair should eliminate the identified defect, preserve the model's overall functionality and, ideally, provide correctness guarantees. Existing approaches address this only partially: gradient-based fine-tuning lacks per-instance guarantees and becomes unstable with few defect samples; model editing assumes explicit knowledge replacement rather than behavioral correction; and constraint-based repair is largely restricted to discriminative models with unique target outputs. We present FORGE, a framework for targeted behavioral repair of generative language models that separates defect localization, weight editing, and behavioral verification into independent stages. Its core is a repair abstraction that converts localized defective generation into explicit optimization objectives, enabling verification-oriented repair techniques to operate on autoregressive generation. FORGE is editing-mechanism agnostic: we instantiate it with (1) a constraint-based quadratic optimization method that provides per-sample repair certificates and (2) a null-space projection editor that minimizes interference with the original model distribution, both under the same localization and verification protocol. On five open-source LLMs, FORGE consistently achieves larger reductions in bias and toxicity than gradient-based fine-tuning with minor perplexity degradation. The two backends exhibit complementary performance across architectures, which a lightweight causal probe traces to where toxicity-related signals concentrate. FORGE also remains effective with only a handful of defective examples, where conventional fine-tuning often oscillates or fails to converge.

Momentum

Related topics

Latest papers 53