{"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-with-canonical-examples","title":"Model Editing with Canonical Examples","arxiv_id":"2402.06155","date":"2024-02-09","proceeding":null,"authors":["John Hewitt","Sarah Chen","Lanruo Lora Xie","Edward Adams","Percy Liang","Christopher D. Manning"],"abstract":"We introduce model editing with canonical examples, a setting in which (1) a single learning example is provided per desired behavior, (2) evaluation is performed exclusively out-of-distribution, and (3) deviation from an initial model is strictly limited. A canonical example is a simple instance of good behavior, e.g., The capital of Mauritius is Port Louis) or bad behavior, e.g., An aspect of researchers is coldhearted). The evaluation set contains more complex examples of each behavior (like a paragraph in which the capital of Mauritius is called for.) We create three datasets and modify three more for model editing with canonical examples, covering knowledge-intensive improvements, social bias mitigation, and syntactic edge cases. In our experiments on Pythia language models, we find that LoRA outperforms full finetuning and MEMIT. We then turn to the Backpack language model architecture because it is intended to enable targeted improvement. The Backpack defines a large bank of sense vectors--a decomposition of the different uses of each word--which are weighted and summed to form the output logits of the model. We propose sense finetuning, which selects and finetunes a few ($\\approx$ 10) sense vectors for each canonical example, and find that it outperforms other finetuning methods, e.g., 4.8% improvement vs 0.3%. Finally, we improve GPT-J-6B by an inference-time ensemble with just the changes from sense finetuning of a 35x smaller Backpack, in one setting outperforming editing GPT-J itself (4.1% vs 1.0%).","url_abs":"https://arxiv.org/abs/2402.06155v1","url_pdf":"https://arxiv.org/pdf/2402.06155v1.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-with-canonical-examples","repo_url":"https://github.com/john-hewitt/model-editing-canonical-examples","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"model-editing","task_name":"Model Editing"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"pythia","method_name":"Pythia"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.06155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.06155"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/john-hewitt/model-editing-canonical-examples","reach":{"status":"ok"}}],"summary":{"ran":2,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"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":4,"samples":[{"code_sha256_prefix":"4369707ff9e9692c","entry":"score_pair_suffix","repo":"john-hewitt/model-editing-canonical-examples","repo_kind":"official","path":"utils.py","file_url":"https://github.com/john-hewitt/model-editing-canonical-examples/blob/HEAD/utils.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":"4369707ff9e9692c"}},{"code_sha256_prefix":"8bd8b53e9b68ce1b","entry":"score_suffix","repo":"john-hewitt/model-editing-canonical-examples","repo_kind":"official","path":"utils.py","file_url":"https://github.com/john-hewitt/model-editing-canonical-examples/blob/HEAD/utils.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":"8bd8b53e9b68ce1b"}},{"code_sha256_prefix":"10a192294fdc723a","entry":"load_model","repo":"john-hewitt/model-editing-canonical-examples","repo_kind":"official","path":"utils.py","file_url":"https://github.com/john-hewitt/model-editing-canonical-examples/blob/HEAD/utils.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":"10a192294fdc723a"}},{"code_sha256_prefix":"a404376e15b72ded","entry":"regularized_attn_weight_per_example","repo":"john-hewitt/model-editing-canonical-examples","repo_kind":"official","path":"importance.py","file_url":"https://github.com/john-hewitt/model-editing-canonical-examples/blob/HEAD/importance.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":"a404376e15b72ded"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}