{"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/democratizing-large-language-models-via","title":"Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning","arxiv_id":"2402.04401","date":"2024-02-06","proceeding":null,"authors":["Zhaoxuan Tan","Qingkai Zeng","Yijun Tian","Zheyuan Liu","Bing Yin","Meng Jiang"],"abstract":"Personalization in large language models (LLMs) is increasingly important, aiming to align the LLMs' interactions, content, and recommendations with individual user preferences. Recent advances have highlighted effective prompt design by enriching user queries with non-parametric knowledge through behavior history retrieval and textual profiles. However, these methods faced limitations due to a lack of model ownership, resulting in constrained customization and privacy issues, and often failed to capture complex, dynamic user behavior patterns. To address these shortcomings, we introduce One PEFT Per User (OPPU), employing personalized parameter-efficient fine-tuning (PEFT) modules to store user-specific behavior patterns and preferences. By plugging in personal PEFT parameters, users can own and use their LLMs individually. OPPU integrates parametric user knowledge in the personal PEFT parameters with non-parametric knowledge from retrieval and profiles, adapting LLMs to user behavior shifts. Experimental results demonstrate that OPPU significantly outperforms existing prompt-based methods across seven diverse tasks in the LaMP benchmark. Further studies reveal OPPU's enhanced capabilities in handling user behavior shifts, modeling users at different activity levels, maintaining robustness across various user history formats, and displaying versatility with different PEFT methods.","url_abs":"https://arxiv.org/abs/2402.04401v2","url_pdf":"https://arxiv.org/pdf/2402.04401v2.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":"democratizing-large-language-models-via","repo_url":"https://github.com/tamsiuhin/oppu","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"democratizing-large-language-models-via","repo_url":"https://github.com/TamSiuhin/Per-Pcs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.04401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04401"}},"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/TamSiuhin/Per-Pcs","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tamsiuhin/oppu","reach":{"status":"ok"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"7e86bfcbb4f77726","entry":"extract_citation_title","repo":"tamsiuhin/oppu","repo_kind":"official","path":"utils.py","file_url":"https://github.com/tamsiuhin/oppu/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7e86bfcbb4f77726"}},{"code_sha256_prefix":"d9ca2b9e65dd8669","entry":"extract_movie","repo":"tamsiuhin/oppu","repo_kind":"official","path":"utils.py","file_url":"https://github.com/tamsiuhin/oppu/blob/HEAD/utils.py","link_basis":"harvester_set","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":"d9ca2b9e65dd8669"}},{"code_sha256_prefix":"45a6039a5ec5e51b","entry":"extract_option","repo":"tamsiuhin/oppu","repo_kind":"official","path":"utils.py","file_url":"https://github.com/tamsiuhin/oppu/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"45a6039a5ec5e51b"}},{"code_sha256_prefix":"b245e168befbde33","entry":"postprocess_text_classification","repo":"tamsiuhin/oppu","repo_kind":"official","path":"eval/evaluation.py","file_url":"https://github.com/tamsiuhin/oppu/blob/HEAD/eval/evaluation.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":"b245e168befbde33"}},{"code_sha256_prefix":"b7703ba9d7775bae","entry":"postprocess_text_generation","repo":"tamsiuhin/oppu","repo_kind":"official","path":"eval/evaluation.py","file_url":"https://github.com/tamsiuhin/oppu/blob/HEAD/eval/evaluation.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":"b7703ba9d7775bae"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}