{"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/neighboring-perturbations-of-knowledge","title":"Neighboring Perturbations of Knowledge Editing on Large Language Models","arxiv_id":"2401.17623","date":"2024-01-31","proceeding":null,"authors":["Jun-Yu Ma","Zhen-Hua Ling","Ningyu Zhang","Jia-Chen Gu"],"abstract":"Despite their exceptional capabilities, large language models (LLMs) are prone to generating unintended text due to false or outdated knowledge. Given the resource-intensive nature of retraining LLMs, there has been a notable increase in the development of knowledge editing. However, current approaches and evaluations rarely explore the perturbation of editing on neighboring knowledge. This paper studies whether updating new knowledge to LLMs perturbs the neighboring knowledge encapsulated within them. Specifically, we seek to figure out whether appending a new answer into an answer list to a factual question leads to catastrophic forgetting of original correct answers in this list, as well as unintentional inclusion of incorrect answers. A metric of additivity is introduced and a benchmark dubbed as Perturbation Evaluation of Appending Knowledge (PEAK) is constructed to evaluate the degree of perturbation to neighboring knowledge when appending new knowledge. Besides, a plug-and-play framework termed Appending via Preservation and Prevention (APP) is proposed to mitigate the neighboring perturbation by maintaining the integrity of the answer list. Experiments demonstrate the effectiveness of APP coupling with four editing methods on four LLMs. The code and data are available at https://github.com/mjy1111/PEAK.","url_abs":"https://arxiv.org/abs/2401.17623v2","url_pdf":"https://arxiv.org/pdf/2401.17623v2.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":"neighboring-perturbations-of-knowledge","repo_url":"https://github.com/mjy1111/peak","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"knowledge-editing","task_name":"knowledge editing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.17623","atlas_url":"https://app.syntology.ai/?focus=2401.17623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17623"}},"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":"deterministic:regex_extraction","url":"https://github.com/mjy1111/PEAK","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mjy1111/peak","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran":6,"unverified":8},"by_repo_kind":{"official":{"samples":16,"ran":8,"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":16,"samples":[{"code_sha256_prefix":"27659a9c234ffb11","entry":"binary_log_probs","repo":"mjy1111/PEAK","repo_kind":"official","path":"easyeditor/trainer/losses.py","file_url":"https://github.com/mjy1111/PEAK/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":"95de8d172a81de57","entry":"get_states","repo":"mjy1111/PEAK","repo_kind":"official","path":"experiments/sweep.py","file_url":"https://github.com/mjy1111/PEAK/blob/HEAD/experiments/sweep.py","link_basis":"first_harvest_node","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":"95de8d172a81de57"}},{"code_sha256_prefix":"920b394e7ad80c53","entry":"hierarchical_subsequence","repo":"mjy1111/PEAK","repo_kind":"official","path":"easyeditor/util/nethook.py","file_url":"https://github.com/mjy1111/PEAK/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":"fb9a42215a0bc4b6","entry":"rank_compute_affect","repo":"mjy1111/PEAK","repo_kind":"official","path":"experiments/summarize.py","file_url":"https://github.com/mjy1111/PEAK/blob/HEAD/experiments/summarize.py","link_basis":"first_harvest_node","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":"fb9a42215a0bc4b6"}},{"code_sha256_prefix":"1c0667f9de68c407","entry":"rank_compute_affect_post","repo":"mjy1111/PEAK","repo_kind":"official","path":"experiments/summarize.py","file_url":"https://github.com/mjy1111/PEAK/blob/HEAD/experiments/summarize.py","link_basis":"first_harvest_node","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":"1c0667f9de68c407"}},{"code_sha256_prefix":"70f6ab8bde55420e","entry":"recursive_copy","repo":"mjy1111/PEAK","repo_kind":"official","path":"easyeditor/util/nethook.py","file_url":"https://github.com/mjy1111/PEAK/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":"900072c14fd21de8","entry":"sigmoid_function","repo":"mjy1111/PEAK","repo_kind":"official","path":"experiments/summarize.py","file_url":"https://github.com/mjy1111/PEAK/blob/HEAD/experiments/summarize.py","link_basis":"first_harvest_node","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":"900072c14fd21de8"}},{"code_sha256_prefix":"440ff98c2b1ae1aa","entry":"subsequence","repo":"mjy1111/PEAK","repo_kind":"official","path":"easyeditor/util/nethook.py","file_url":"https://github.com/mjy1111/PEAK/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":"1bd195094160c941","entry":"BiEditor","repo":"mjy1111/peak","repo_kind":"official","path":"easyeditor/editors/add_editor.py","file_url":"https://github.com/mjy1111/peak/blob/HEAD/easyeditor/editors/add_editor.py","link_basis":"first_harvest_node","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":"1bd195094160c941"}},{"code_sha256_prefix":"6780715b512fe3d5","entry":"get_model","repo":"mjy1111/PEAK","repo_kind":"official","path":"easyeditor/trainer/models.py","file_url":"https://github.com/mjy1111/PEAK/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":"6780715b512fe3d5"}},{"code_sha256_prefix":"2defe42cf1a7f301","entry":"get_tokenizer","repo":"mjy1111/PEAK","repo_kind":"official","path":"easyeditor/trainer/models.py","file_url":"https://github.com/mjy1111/PEAK/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":"mjy1111/PEAK","repo_kind":"official","path":"easyeditor/trainer/losses.py","file_url":"https://github.com/mjy1111/PEAK/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":"f962fe356f9b4c37","entry":"multiclass_log_probs","repo":"mjy1111/PEAK","repo_kind":"official","path":"easyeditor/trainer/losses.py","file_url":"https://github.com/mjy1111/PEAK/blob/HEAD/easyeditor/trainer/losses.py","link_basis":"first_harvest_node","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":"f962fe356f9b4c37"}},{"code_sha256_prefix":"f178cf7f2e0fcb20","entry":"rank_compute_affect","repo":"mjy1111/peak","repo_kind":"official","path":"experiments/summarize.py","file_url":"https://github.com/mjy1111/peak/blob/HEAD/experiments/summarize.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f178cf7f2e0fcb20"}},{"code_sha256_prefix":"feda57d8d52b2a50","entry":"rank_compute_affect_post","repo":"mjy1111/peak","repo_kind":"official","path":"experiments/summarize.py","file_url":"https://github.com/mjy1111/peak/blob/HEAD/experiments/summarize.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"feda57d8d52b2a50"}},{"code_sha256_prefix":"53ccdc55be933162","entry":"sigmoid_function","repo":"mjy1111/peak","repo_kind":"official","path":"experiments/summarize.py","file_url":"https://github.com/mjy1111/peak/blob/HEAD/experiments/summarize.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"53ccdc55be933162"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}