{"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/long-form-evaluation-of-model-editing","title":"Long-form evaluation of model editing","arxiv_id":"2402.09394","date":"2024-02-14","proceeding":null,"authors":["Domenic Rosati","Robie Gonzales","Jinkun Chen","Xuemin Yu","Melis Erkan","Yahya Kayani","Satya Deepika Chavatapalli","Frank Rudzicz","Hassan Sajjad"],"abstract":"Evaluations of model editing currently only use the `next few token' completions after a prompt. As a result, the impact of these methods on longer natural language generation is largely unknown. We introduce long-form evaluation of model editing (LEME) a novel evaluation protocol that measures the efficacy and impact of model editing in long-form generative settings. Our protocol consists of a machine-rated survey and a classifier which correlates well with human ratings. Importantly, we find that our protocol has very little relationship with previous short-form metrics (despite being designed to extend efficacy, generalization, locality, and portability into a long-form setting), indicating that our method introduces a novel set of dimensions for understanding model editing methods. Using this protocol, we benchmark a number of model editing techniques and present several findings including that, while some methods (ROME and MEMIT) perform well in making consistent edits within a limited scope, they suffer much more from factual drift than other methods. Finally, we present a qualitative analysis that illustrates common failure modes in long-form generative settings including internal consistency, lexical cohesion, and locality issues.","url_abs":"https://arxiv.org/abs/2402.09394v2","url_pdf":"https://arxiv.org/pdf/2402.09394v2.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":"long-form-evaluation-of-model-editing","repo_url":"https://github.com/domenicrosati/longform-evaluation-model-editing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"form","task_name":"Form"},{"task_slug":"model-editing","task_name":"Model Editing"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.09394","atlas_url":"https://app.syntology.ai/?focus=2402.09394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09394"}},"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/domenicrosati/longform-evaluation-model-editing","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"6be6c7d3f948ef58","entry":"calculate_perplexity","repo":"domenicrosati/longform-evaluation-model-editing","repo_kind":"official","path":"src/automatic_metrics.py","file_url":"https://github.com/domenicrosati/longform-evaluation-model-editing/blob/HEAD/src/automatic_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6be6c7d3f948ef58"}},{"code_sha256_prefix":"224fc50d0f23cc6f","entry":"get_overlap_measures","repo":"domenicrosati/longform-evaluation-model-editing","repo_kind":"official","path":"src/automatic_metrics.py","file_url":"https://github.com/domenicrosati/longform-evaluation-model-editing/blob/HEAD/src/automatic_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"224fc50d0f23cc6f"}},{"code_sha256_prefix":"be1f4b21a6bfc222","entry":"sentence_splitter","repo":"domenicrosati/longform-evaluation-model-editing","repo_kind":"official","path":"src/llm_annotator.py","file_url":"https://github.com/domenicrosati/longform-evaluation-model-editing/blob/HEAD/src/llm_annotator.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be1f4b21a6bfc222"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}