{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/model-editing-can-hurt-general-abilities-of","title":"Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue","arxiv_id":"2401.04700","date":"2024-01-09","proceeding":null,"authors":["Jia-Chen Gu","Hao-Xiang Xu","Jun-Yu Ma","Pan Lu","Zhen-Hua Ling","Kai-Wei Chang","Nanyun Peng"],"abstract":"Model editing is a technique that edits the large language models (LLMs) with updated knowledge to alleviate hallucinations without resource-intensive retraining. While current model editing methods can effectively modify a model's behavior within a specific area of interest, they often overlook the potential unintended side effects on the general abilities of LLMs such as reasoning, natural language inference, and question answering. In this paper, we raise concerns that model editing's improvements on factuality may come at the cost of a significant degradation of the model's general abilities. We systematically analyze the side effects by evaluating four popular editing methods on three LLMs across eight representative tasks. Our extensive empirical experiments show that it is challenging for current editing methods to simultaneously improve factuality of LLMs and maintain their general abilities. Our analysis reveals that the side effects are caused by model editing altering the original model weights excessively, leading to overfitting to the edited facts. To mitigate this, a method named RECT is proposed to regularize the edit update weights by imposing constraints on their complexity based on the RElative Change in weighT. Evaluation results show that RECT can significantly mitigate the side effects of editing while still maintaining over 94% editing performance.","url_abs":"https://arxiv.org/abs/2401.04700v4","url_pdf":"https://arxiv.org/pdf/2401.04700v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"model-editing-can-hurt-general-abilities-of","repo_url":"https://github.com/jasonforjoy/model-editing-hurt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"model-editing","task_name":"Model Editing"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.04700","atlas_url":"https://app.syntology.ai/?focus=2401.04700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04700"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jasonforjoy/model-editing-hurt","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran":3,"unverified":6},"by_repo_kind":{"official":{"samples":11,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":11,"samples":[{"code_sha256_prefix":"27659a9c234ffb11","entry":"binary_log_probs","repo":"jasonforjoy/model-editing-hurt","repo_kind":"official","path":"easyeditor/trainer/losses.py","file_url":"https://github.com/jasonforjoy/model-editing-hurt/blob/HEAD/easyeditor/trainer/losses.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"27659a9c234ffb11"}},{"code_sha256_prefix":"920b394e7ad80c53","entry":"hierarchical_subsequence","repo":"jasonforjoy/model-editing-hurt","repo_kind":"official","path":"easyeditor/util/nethook.py","file_url":"https://github.com/jasonforjoy/model-editing-hurt/blob/HEAD/easyeditor/util/nethook.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"920b394e7ad80c53"}},{"code_sha256_prefix":"70f6ab8bde55420e","entry":"recursive_copy","repo":"jasonforjoy/model-editing-hurt","repo_kind":"official","path":"easyeditor/util/nethook.py","file_url":"https://github.com/jasonforjoy/model-editing-hurt/blob/HEAD/easyeditor/util/nethook.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"70f6ab8bde55420e"}},{"code_sha256_prefix":"440ff98c2b1ae1aa","entry":"subsequence","repo":"jasonforjoy/model-editing-hurt","repo_kind":"official","path":"easyeditor/util/nethook.py","file_url":"https://github.com/jasonforjoy/model-editing-hurt/blob/HEAD/easyeditor/util/nethook.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"440ff98c2b1ae1aa"}},{"code_sha256_prefix":"cb33571427334815","entry":"tile","repo":"jasonforjoy/model-editing-hurt","repo_kind":"official","path":"easyeditor/trainer/blip2_models/base_model.py","file_url":"https://github.com/jasonforjoy/model-editing-hurt/blob/HEAD/easyeditor/trainer/blip2_models/base_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb33571427334815"}},{"code_sha256_prefix":"0ec9fc2025c16f65","entry":"all_gather_with_grad","repo":"jasonforjoy/model-editing-hurt","repo_kind":"official","path":"easyeditor/trainer/blip2_models/base_model.py","file_url":"https://github.com/jasonforjoy/model-editing-hurt/blob/HEAD/easyeditor/trainer/blip2_models/base_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0ec9fc2025c16f65"}},{"code_sha256_prefix":"a829872cf2507355","entry":"concat_all_gather","repo":"jasonforjoy/model-editing-hurt","repo_kind":"official","path":"easyeditor/trainer/blip2_models/base_model.py","file_url":"https://github.com/jasonforjoy/model-editing-hurt/blob/HEAD/easyeditor/trainer/blip2_models/base_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a829872cf2507355"}},{"code_sha256_prefix":"d2e4c1979dd70b9a","entry":"get_model","repo":"jasonforjoy/model-editing-hurt","repo_kind":"official","path":"easyeditor/trainer/models.py","file_url":"https://github.com/jasonforjoy/model-editing-hurt/blob/HEAD/easyeditor/trainer/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d2e4c1979dd70b9a"}},{"code_sha256_prefix":"2defe42cf1a7f301","entry":"get_tokenizer","repo":"jasonforjoy/model-editing-hurt","repo_kind":"official","path":"easyeditor/trainer/models.py","file_url":"https://github.com/jasonforjoy/model-editing-hurt/blob/HEAD/easyeditor/trainer/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2defe42cf1a7f301"}},{"code_sha256_prefix":"bcc592aa5c1e2bb3","entry":"kl_loc_loss","repo":"jasonforjoy/model-editing-hurt","repo_kind":"official","path":"easyeditor/trainer/losses.py","file_url":"https://github.com/jasonforjoy/model-editing-hurt/blob/HEAD/easyeditor/trainer/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bcc592aa5c1e2bb3"}},{"code_sha256_prefix":"caf658f0bdfae9a9","entry":"multiclass_log_probs","repo":"jasonforjoy/model-editing-hurt","repo_kind":"official","path":"easyeditor/trainer/losses.py","file_url":"https://github.com/jasonforjoy/model-editing-hurt/blob/HEAD/easyeditor/trainer/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"caf658f0bdfae9a9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}