{"url":"/method/rome","slug":"rome","name":"ROME","full_name":"Rank-One Model Editing","full_name_withheld":false,"description_markdown":null,"description_state":"absent","introduced_year":null,"introduced_by":{"title":"Locating and Editing Factual Associations in GPT","paper":"/paper/locating-and-editing-factual-knowledge-in-gpt","first_author":"Kevin Meng","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/locating-and-editing-factual-knowledge-in-gpt"},"source":{"url":"https://arxiv.org/abs/2202.05262v5","title":"Locating and Editing Factual Associations in GPT","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Parameter Norm Penalties","url":"/methods/category/parameter-norm-penalties","pwc_aliases":[]}],"n_papers_tagged":23,"archive_num_papers":23,"papers_newest_first":[{"paper":"/paper/r2r-efficiently-navigating-divergent","title":"R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing","date":"2025-05-27","arxiv_id":"2505.21600","n_code_links":1,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":0}},{"paper":null,"title":"Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?","date":"2025-05-26","arxiv_id":"2505.19855","n_code_links":0,"syntology":null},{"paper":"/paper/related-knowledge-perturbation-matters","title":"Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject","date":"2025-02-08","arxiv_id":"2502.06868","n_code_links":1,"syntology":null},{"paper":null,"title":"ROME: Robust Model Ensembling for Semantic Communication Against Semantic Jamming Attacks","date":"2025-01-02","arxiv_id":"2501.01172","n_code_links":0,"syntology":null},{"paper":"/paper/the-fall-of-rome-understanding-the-collapse","title":"Understanding the Collapse of LLMs in Model Editing","date":"2024-06-17","arxiv_id":"2406.11263","n_code_links":1,"syntology":{"ran":1,"of":2,"unverified":1,"pointer_only":1}},{"paper":"/paper/is-bigger-edit-batch-size-always-better-an","title":"Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3","date":"2024-05-01","arxiv_id":"2405.00664","n_code_links":1,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":2}},{"paper":"/paper/a-unified-framework-for-model-editing","title":"A Unified Framework for Model Editing","date":"2024-03-21","arxiv_id":"2403.14236","n_code_links":1,"syntology":null},{"paper":"/paper/rebuilding-rome-resolving-model-collapse","title":"Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing","date":"2024-03-11","arxiv_id":"2403.07175","n_code_links":1,"syntology":{"ran":10,"of":15,"unverified":5,"pointer_only":0}},{"paper":null,"title":"ROME: Memorization Insights from Text, Logits and Representation","date":"2024-03-01","arxiv_id":"2403.00510","n_code_links":0,"syntology":null},{"paper":"/paper/how-un-ethical-are-instruction-centric","title":"How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries","date":"2024-02-23","arxiv_id":"2402.15302","n_code_links":1,"syntology":null},{"paper":null,"title":"Robust Multi-Modal Density Estimation","date":"2024-01-19","arxiv_id":"2401.10566","n_code_links":0,"syntology":null},{"paper":"/paper/model-editing-at-scale-leads-to-gradual-and","title":"Model Editing at Scale leads to Gradual and Catastrophic Forgetting","date":"2024-01-15","arxiv_id":"2401.07453","n_code_links":1,"syntology":{"ran":7,"of":9,"unverified":2,"pointer_only":9}},{"paper":"/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","n_code_links":2,"syntology":null},{"paper":null,"title":"SHARE: Single-view Human Adversarial REconstruction","date":"2023-12-30","arxiv_id":"2401.00343","n_code_links":0,"syntology":null},{"paper":null,"title":"Trace and Edit Relation Associations in GPT","date":"2023-12-30","arxiv_id":"2401.02976","n_code_links":0,"syntology":null},{"paper":null,"title":"Optimizing Fault-Tolerant Quality-Guaranteed Sensor Deployments for UAV Localization in Critical Areas via Computational Geometry","date":"2023-12-05","arxiv_id":"2312.06667","n_code_links":0,"syntology":null},{"paper":"/paper/rome-evaluating-pre-trained-vision-language","title":"ROME: Evaluating Pre-trained Vision-Language Models on Reasoning beyond Visual Common Sense","date":"2023-10-30","arxiv_id":"2310.19301","n_code_links":1,"syntology":null},{"paper":"/paper/can-sensitive-information-be-deleted-from","title":"Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks","date":"2023-09-29","arxiv_id":"2309.17410","n_code_links":1,"syntology":{"ran":9,"of":14,"unverified":5,"pointer_only":0}},{"paper":"/paper/rome-towards-large-scale-road-surface","title":"RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation","date":"2023-06-20","arxiv_id":"2306.11368","n_code_links":1,"syntology":null},{"paper":"/paper/rome-role-aware-mixture-of-expert-transformer","title":"RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval","date":"2022-06-26","arxiv_id":"2206.12845","n_code_links":1,"syntology":null},{"paper":null,"title":"Realistic One-shot Mesh-based Head Avatars","date":"2022-06-16","arxiv_id":"2206.08343","n_code_links":0,"syntology":null},{"paper":"/paper/rome-a-robust-metric-for-evaluating-natural-1","title":"RoMe: A Robust Metric for Evaluating Natural Language Generation","date":"2022-03-17","arxiv_id":"2203.09183","n_code_links":1,"syntology":null},{"paper":"/paper/locating-and-editing-factual-knowledge-in-gpt","title":"Locating and Editing Factual Associations in GPT","date":"2022-02-10","arxiv_id":"2202.05262","n_code_links":4,"syntology":{"ran":4,"of":15,"unverified":11,"pointer_only":0}}],"papers_shown":23,"tasks":[{"task":"/task/model-editing","name":"Model Editing","papers":9},{"task":"/task/language-modeling","name":"Language Modeling","papers":4},{"task":"/task/language-modelling","name":"Language Modelling","papers":4},{"task":"/task/specificity","name":"Specificity","papers":3},{"task":"/task/knowledge-editing","name":"knowledge editing","papers":3},{"task":"/task/large-language-model","name":"Large Language Model","papers":2},{"task":"/task/memorization","name":"Memorization","papers":2},{"task":"/task/model","name":"model","papers":2},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":1},{"task":"/task/common-sense-reasoning","name":"Common Sense Reasoning","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/density-estimation","name":"Density Estimation","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/in-context-learning","name":"In-Context Learning","papers":1},{"task":"/task/math","name":"Math","papers":1},{"task":"/task/mixture-of-experts","name":"Mixture-of-Experts","papers":1},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":1},{"task":null,"name":"Relation","papers":1},{"task":"/task/relation-extraction","name":"Relation Extraction","papers":1}],"tasks_shown":20,"n_tasks":31,"usage_by_year":[{"year":"2022","papers":4},{"year":"2023","papers":6},{"year":"2024","papers":9},{"year":"2025","papers":4}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/rome"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}