{"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/unmemorization-in-large-language-models-via","title":"UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models","arxiv_id":"2402.10052","date":"2024-02-15","proceeding":null,"authors":["Yijiang River Dong","Hongzhou Lin","Mikhail Belkin","Ramon Huerta","Ivan Vulić"],"abstract":"Mitigating the retention of sensitive or private information in large language models is essential for enhancing privacy and safety. Existing unlearning methods, like Gradient Ascent and Negative Preference Optimization, directly tune models to remove unwanted information. However, these methods often become unstable because they fine-tune by maximizing cross-entropy loss, which is the opposite of traditional loss minimization in learning. This reversal creates instability, especially on larger datasets, as the model struggles to balance unlearning with maintaining language capacity, leading to over-unlearning. In this paper, we introduce UnDIAL (Unlearning via Self-Distillation on Adjusted Logits), a novel and robust unlearning method. Our approach leverages self-distillation to adjust logits and selectively reduce the influence of targeted tokens. This technique ensures smooth convergence and avoids catastrophic forgetting, even in challenging unlearning tasks with large datasets and sequential unlearning requests. Extensive experiments show that UnDIAL can achieve both robustness in unlearning and scalability while maintaining stable training dynamics and resilience to hyperparameter tuning.","url_abs":"https://arxiv.org/abs/2402.10052v2","url_pdf":"https://arxiv.org/pdf/2402.10052v2.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":"unmemorization-in-large-language-models-via","repo_url":"https://github.com/dong-river/llm_unlearning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2402.10052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10052"}},"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/dong-river/llm_unlearning","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"5b92c2cc18c12907","entry":"create_experiment_commands","repo":"dong-river/llm_unlearning","repo_kind":"official","path":"exp/create_exp_baselines.py","file_url":"https://github.com/dong-river/llm_unlearning/blob/HEAD/exp/create_exp_baselines.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":"5b92c2cc18c12907"}},{"code_sha256_prefix":"884483b6e5ec4e2c","entry":"parse_data","repo":"dong-river/llm_unlearning","repo_kind":"official","path":"parse_logs.py","file_url":"https://github.com/dong-river/llm_unlearning/blob/HEAD/parse_logs.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"884483b6e5ec4e2c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}