{"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-state-arithmetic-for-machine-unlearning","title":"Model State Arithmetic for Machine Unlearning","arxiv_id":"2506.20941","date":"2025-06-26","proceeding":null,"authors":["Keivan Rezaei","Mehrdad Saberi","Abhilasha Ravichander","Soheil Feizi"],"abstract":"Large language models are trained on massive corpora of web data, which may include private data, copyrighted material, factually inaccurate data, or data that degrades model performance. Eliminating the influence of such problematic datapoints through complete retraining -- by repeatedly pretraining the model on datasets that exclude these specific instances -- is computationally prohibitive. For this reason, unlearning algorithms have emerged that aim to eliminate the influence of particular datapoints, while otherwise preserving the model -- at a low computational cost. However, precisely estimating and undoing the influence of individual datapoints has proved to be challenging. In this work, we propose a new algorithm, MSA, for estimating and undoing the influence of datapoints -- by leveraging model checkpoints i.e. artifacts capturing model states at different stages of pretraining. Our experimental results demonstrate that MSA consistently outperforms existing machine unlearning algorithms across multiple benchmarks, models, and evaluation metrics, suggesting that MSA could be an effective approach towards more flexible large language models that are capable of data erasure.","url_abs":"https://arxiv.org/abs/2506.20941v1","url_pdf":"https://arxiv.org/pdf/2506.20941v1.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-state-arithmetic-for-machine-unlearning","repo_url":"https://github.com/mehrdadsaberi/msa_unlearning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-unlearning","task_name":"Machine Unlearning"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.20941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.20941"}},"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/mehrdadsaberi/msa_unlearning","reach":null}],"summary":{"ran_draft_wrong":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":0,"samples":[{"code_sha256_prefix":"83396ec95592fb23","entry":"load_yaml","repo":"mehrdadsaberi/msa_unlearning","repo_kind":"official","path":"src/finetune.py","file_url":"https://github.com/mehrdadsaberi/msa_unlearning/blob/HEAD/src/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"83396ec95592fb23"}},{"code_sha256_prefix":"fd8d7039bbcb386b","entry":"load_yaml","repo":"mehrdadsaberi/msa_unlearning","repo_kind":"official","path":"src/tv_unlearn.py","file_url":"https://github.com/mehrdadsaberi/msa_unlearning/blob/HEAD/src/tv_unlearn.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fd8d7039bbcb386b"}},{"code_sha256_prefix":"fba3196222b060a3","entry":"load_model","repo":"mehrdadsaberi/msa_unlearning","repo_kind":"official","path":"src/tv_unlearn.py","file_url":"https://github.com/mehrdadsaberi/msa_unlearning/blob/HEAD/src/tv_unlearn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fba3196222b060a3"}},{"code_sha256_prefix":"aa93c2f32ef7df6c","entry":"main","repo":"mehrdadsaberi/msa_unlearning","repo_kind":"official","path":"src/tv_unlearn.py","file_url":"https://github.com/mehrdadsaberi/msa_unlearning/blob/HEAD/src/tv_unlearn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa93c2f32ef7df6c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}