{"url":"/task/model-editing","name":"Model Editing","slug":"model-editing","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":193,"papers_with_code":107,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":1,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/knowedit","name":"KnowEdit","full_name":"","num_papers_in_archive":4}],"subtasks":[{"url":"/task/knowledge-editing","name":"knowledge editing"}],"parent_tasks":[{"url":"/task/3d-human-action-recognition","name":"3D Action Recognition"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":107,"tagged_in_all":193,"items":[{"url":"/paper/editing-large-language-models-problems","title":"Editing Large Language Models: Problems, Methods, and Opportunities","date":"2023-05-22","arxiv_id":"2305.13172","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/locating-and-editing-factual-knowledge-in-gpt","title":"Locating and Editing Factual Associations in GPT","date":"2022-02-10","arxiv_id":"2202.05262","repositories_listed":4,"syntology":{"n":15,"n_ran":4,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/pyvene-a-library-for-understanding-and","title":"pyvene: A Library for Understanding and Improving PyTorch Models via Interventions","date":"2024-03-12","arxiv_id":"2403.07809","repositories_listed":3,"syntology":{"n":10,"n_ran":1,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/sparse-autoencoders-find-highly-interpretable","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","date":"2023-09-15","arxiv_id":"2309.08600","repositories_listed":3,"syntology":{"n":11,"n_ran":4,"n_unverified":7,"n_pointer_only":5}},{"url":"/paper/fast-model-editing-at-scale-1","title":"Fast Model Editing at Scale","date":"2021-10-21","arxiv_id":"2110.11309","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/the-mirage-of-model-editing-revisiting","title":"The Mirage of Model Editing: Revisiting Evaluation in the Wild","date":"2025-02-16","arxiv_id":"2502.11177","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/neuron-level-sequential-editing-for-large","title":"Neuron-Level Sequential Editing for Large Language Models","date":"2024-10-05","arxiv_id":"2410.04045","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":7}},{"url":"/paper/alphaedit-null-space-constrained-knowledge","title":"AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models","date":"2024-10-03","arxiv_id":"2410.02355","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/2409-14144","title":"Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis","date":"2024-09-21","arxiv_id":"2409.14144","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/targeted-latent-adversarial-training-improves","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","date":"2024-07-22","arxiv_id":"2407.15549","repositories_listed":2,"syntology":{"n":11,"n_ran":5,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/detox-toxic-subspace-projection-for-model","title":"Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity","date":"2024-05-22","arxiv_id":"2405.13967","repositories_listed":2,"syntology":{"n":12,"n_ran":7,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/a-comprehensive-study-of-knowledge-editing","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","date":"2024-01-02","arxiv_id":"2401.01286","repositories_listed":2,"syntology":null},{"url":"/paper/editing-implicit-assumptions-in-text-to-image","title":"Editing Implicit Assumptions in Text-to-Image Diffusion Models","date":"2023-03-14","arxiv_id":"2303.08084","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/interpretability-then-what-editing-machine","title":"Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Values","date":"2022-06-30","arxiv_id":"2206.15465","repositories_listed":2,"syntology":null},{"url":"/paper/model-editing-as-a-double-edged-sword","title":"Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm","date":"2025-06-25","arxiv_id":"2506.20606","repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-safety-fallback-in-editing-based","title":"Mitigating Safety Fallback in Editing-based Backdoor Injection on LLMs","date":"2025-06-16","arxiv_id":"2506.13285","repositories_listed":1,"syntology":null},{"url":"/paper/drop-dropout-on-single-epoch-language-model","title":"Drop Dropout on Single-Epoch Language Model Pretraining","date":"2025-05-30","arxiv_id":"2505.24788","repositories_listed":1,"syntology":null},{"url":"/paper/unierase-unlearning-token-as-a-universal","title":"UniErase: Unlearning Token as a Universal Erasure Primitive for Language Models","date":"2025-05-21","arxiv_id":"2505.15674","repositories_listed":1,"syntology":null},{"url":"/paper/lyaplock-bounded-knowledge-preservation-in","title":"LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing","date":"2025-05-21","arxiv_id":"2505.15702","repositories_listed":1,"syntology":null},{"url":"/paper/ultraedit-training-subject-and-memory-free","title":"UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Large Language Models","date":"2025-05-20","arxiv_id":"2505.14679","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/cross-model-transfer-of-task-vectors-via-few","title":"Cross-Model Transfer of Task Vectors via Few-Shot Orthogonal Alignment","date":"2025-05-17","arxiv_id":"2505.12021","repositories_listed":1,"syntology":null},{"url":"/paper/namet-robust-massive-model-editing-via-noise","title":"NAMET: Robust Massive Model Editing via Noise-Aware Memory Optimization","date":"2025-05-17","arxiv_id":"2505.11876","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/efficient-model-editing-with-task-localized","title":"Efficient Model Editing with Task-Localized Sparse Fine-tuning","date":"2025-04-03","arxiv_id":"2504.02620","repositories_listed":1,"syntology":null},{"url":"/paper/localized-definitions-and-distributed","title":"Localized Definitions and Distributed Reasoning: A Proof-of-Concept Mechanistic Interpretability Study via Activation Patching","date":"2025-04-03","arxiv_id":"2504.02976","repositories_listed":1,"syntology":null},{"url":"/paper/leaking-lora-an-evaluation-of-password-leaks","title":"Leaking LoRa: An Evaluation of Password Leaks and Knowledge Storage in Large Language Models","date":"2025-03-29","arxiv_id":"2504.00031","repositories_listed":1,"syntology":null},{"url":"/paper/biasedit-debiasing-stereotyped-language","title":"BiasEdit: Debiasing Stereotyped Language Models via Model Editing","date":"2025-03-11","arxiv_id":"2503.08588","repositories_listed":1,"syntology":null},{"url":"/paper/speed-scalable-precise-and-efficient-concept","title":"SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models","date":"2025-03-10","arxiv_id":"2503.07392","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/come-an-unlearning-based-approach-to-conflict","title":"CoME: An Unlearning-based Approach to Conflict-free Model Editing","date":"2025-02-20","arxiv_id":"2502.15826","repositories_listed":1,"syntology":null},{"url":"/paper/injecting-universal-jailbreak-backdoors-into","title":"Injecting Universal Jailbreak Backdoors into LLMs in Minutes","date":"2025-02-09","arxiv_id":"2502.10438","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/2502-05759","title":"Reinforced Lifelong Editing for Language Models","date":"2025-02-09","arxiv_id":"2502.05759","repositories_listed":1,"syntology":null}],"syntology_records":16,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}