{"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/learning-to-refuse-towards-mitigating-privacy","title":"Learning to Refuse: Towards Mitigating Privacy Risks in LLMs","arxiv_id":"2407.10058","date":"2024-07-14","proceeding":null,"authors":["Zhenhua Liu","Tong Zhu","Chuanyuan Tan","Wenliang Chen"],"abstract":"Large language models (LLMs) exhibit remarkable capabilities in understanding and generating natural language. However, these models can inadvertently memorize private information, posing significant privacy risks. This study addresses the challenge of enabling LLMs to protect specific individuals' private data without the need for complete retraining. We propose \\return, a Real-world pErsonal daTa UnleaRNing dataset, comprising 2,492 individuals from Wikipedia with associated QA pairs, to evaluate machine unlearning (MU) methods for protecting personal data in a realistic scenario. Additionally, we introduce the Name-Aware Unlearning Framework (NAUF) for Privacy Protection, which enables the model to learn which individuals' information should be protected without affecting its ability to answer questions related to other unrelated individuals. Our extensive experiments demonstrate that NAUF achieves a state-of-the-art average unlearning score, surpassing the best baseline method by 5.65 points, effectively protecting target individuals' personal data while maintaining the model's general capabilities.","url_abs":"https://arxiv.org/abs/2407.10058v2","url_pdf":"https://arxiv.org/pdf/2407.10058v2.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":"learning-to-refuse-towards-mitigating-privacy","repo_url":"https://github.com/zhliu0106/learning-to-refuse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-unlearning","task_name":"Machine Unlearning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.10058","atlas_url":"https://app.syntology.ai/?focus=2407.10058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10058"}},"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/zhliu0106/learning-to-refuse","reach":{"status":"ok"}}],"summary":{"ran":6},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":6,"samples":[{"code_sha256_prefix":"c1a969d76dae6c3d","entry":"filter_out_person","repo":"zhliu0106/learning-to-refuse","repo_kind":"official","path":"process_data/filtering.py","file_url":"https://github.com/zhliu0106/learning-to-refuse/blob/HEAD/process_data/filtering.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":"c1a969d76dae6c3d"}},{"code_sha256_prefix":"a4dd4eb5709c2a36","entry":"generate_prompt","repo":"zhliu0106/learning-to-refuse","repo_kind":"official","path":"process_data/augmentation.py","file_url":"https://github.com/zhliu0106/learning-to-refuse/blob/HEAD/process_data/augmentation.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":"a4dd4eb5709c2a36"}},{"code_sha256_prefix":"fe88e7af8e255442","entry":"load_filtered_personqa","repo":"zhliu0106/learning-to-refuse","repo_kind":"official","path":"process_data/construction.py","file_url":"https://github.com/zhliu0106/learning-to-refuse/blob/HEAD/process_data/construction.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":"fe88e7af8e255442"}},{"code_sha256_prefix":"30889d3bca9a6056","entry":"load_model_prediction","repo":"zhliu0106/learning-to-refuse","repo_kind":"official","path":"process_data/filtering.py","file_url":"https://github.com/zhliu0106/learning-to-refuse/blob/HEAD/process_data/filtering.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":"30889d3bca9a6056"}},{"code_sha256_prefix":"d551e8dc744dd824","entry":"load_question_template","repo":"zhliu0106/learning-to-refuse","repo_kind":"official","path":"process_data/augmentation.py","file_url":"https://github.com/zhliu0106/learning-to-refuse/blob/HEAD/process_data/augmentation.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":"d551e8dc744dd824"}},{"code_sha256_prefix":"725ec8b577008818","entry":"split_train_eval","repo":"zhliu0106/learning-to-refuse","repo_kind":"official","path":"process_data/construction.py","file_url":"https://github.com/zhliu0106/learning-to-refuse/blob/HEAD/process_data/construction.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":"725ec8b577008818"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}