{"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/do-unlearning-methods-remove-information-from","title":"Do Unlearning Methods Remove Information from Language Model Weights?","arxiv_id":"2410.08827","date":"2024-10-11","proceeding":null,"authors":["Aghyad Deeb","Fabien Roger"],"abstract":"Large Language Models' knowledge of how to perform cyber-security attacks, create bioweapons, and manipulate humans poses risks of misuse. Previous work has proposed methods to unlearn this knowledge. Historically, it has been unclear whether unlearning techniques are removing information from the model weights or just making it harder to access. To disentangle these two objectives, we propose an adversarial evaluation method to test for the removal of information from model weights: we give an attacker access to some facts that were supposed to be removed, and using those, the attacker tries to recover other facts from the same distribution that cannot be guessed from the accessible facts. We show that using fine-tuning on the accessible facts can recover 88% of the pre-unlearning accuracy when applied to current unlearning methods, revealing the limitations of these methods in removing information from the model weights.","url_abs":"https://arxiv.org/abs/2410.08827v2","url_pdf":"https://arxiv.org/pdf/2410.08827v2.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":"do-unlearning-methods-remove-information-from","repo_url":"https://github.com/aghyad-deeb/unlearning_evaluation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.08827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08827"}},"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/aghyad-deeb/unlearning_evaluation","reach":null}],"summary":{"ran_draft_wrong":8,"ran_honours":1},"by_repo_kind":{"official":{"samples":9,"ran":9,"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":9,"samples":[{"code_sha256_prefix":"814f2de8f4bd281e","entry":"create_prompt","repo":"aghyad-deeb/unlearning_evaluation","repo_kind":"official","path":"unlearn_corpus.py","file_url":"https://github.com/aghyad-deeb/unlearning_evaluation/blob/HEAD/unlearn_corpus.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"814f2de8f4bd281e"}},{"code_sha256_prefix":"246c7ef8f90b3e7e","entry":"create_prompt","repo":"aghyad-deeb/unlearning_evaluation","repo_kind":"official","path":"finetune_corpus.py","file_url":"https://github.com/aghyad-deeb/unlearning_evaluation/blob/HEAD/finetune_corpus.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"246c7ef8f90b3e7e"}},{"code_sha256_prefix":"0260364dcc364961","entry":"flatten_dict","repo":"aghyad-deeb/unlearning_evaluation","repo_kind":"official","path":"pipeline.py","file_url":"https://github.com/aghyad-deeb/unlearning_evaluation/blob/HEAD/pipeline.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0260364dcc364961"}},{"code_sha256_prefix":"2efa3c1f8edf74e1","entry":"get_current_time","repo":"aghyad-deeb/unlearning_evaluation","repo_kind":"official","path":"pipeline.py","file_url":"https://github.com/aghyad-deeb/unlearning_evaluation/blob/HEAD/pipeline.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"none","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2efa3c1f8edf74e1"}},{"code_sha256_prefix":"d5b6806fbf7e337a","entry":"get_log_range","repo":"aghyad-deeb/unlearning_evaluation","repo_kind":"official","path":"pipeline.py","file_url":"https://github.com/aghyad-deeb/unlearning_evaluation/blob/HEAD/pipeline.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d5b6806fbf7e337a"}},{"code_sha256_prefix":"58b52bbe2ca25d7f","entry":"make_k_shot","repo":"aghyad-deeb/unlearning_evaluation","repo_kind":"official","path":"unlearn_corpus.py","file_url":"https://github.com/aghyad-deeb/unlearning_evaluation/blob/HEAD/unlearn_corpus.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"58b52bbe2ca25d7f"}},{"code_sha256_prefix":"b746533fcdfaa51d","entry":"make_k_shot","repo":"aghyad-deeb/unlearning_evaluation","repo_kind":"official","path":"finetune_corpus.py","file_url":"https://github.com/aghyad-deeb/unlearning_evaluation/blob/HEAD/finetune_corpus.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b746533fcdfaa51d"}},{"code_sha256_prefix":"ee7b95c55394f703","entry":"sample_tokens","repo":"aghyad-deeb/unlearning_evaluation","repo_kind":"official","path":"unlearn_corpus.py","file_url":"https://github.com/aghyad-deeb/unlearning_evaluation/blob/HEAD/unlearn_corpus.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ee7b95c55394f703"}},{"code_sha256_prefix":"9fcc0dfdb46714f9","entry":"sample_tokens","repo":"aghyad-deeb/unlearning_evaluation","repo_kind":"official","path":"finetune_corpus.py","file_url":"https://github.com/aghyad-deeb/unlearning_evaluation/blob/HEAD/finetune_corpus.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9fcc0dfdb46714f9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}