{"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/star-constraint-lora-with-dynamic-active","title":"STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language Models","arxiv_id":"2403.01165","date":"2024-03-02","proceeding":null,"authors":["Linhai Zhang","Jialong Wu","Deyu Zhou","Guoqiang Xu"],"abstract":"Though Large Language Models (LLMs) have demonstrated the powerful capabilities of few-shot learning through prompting methods, supervised training is still necessary for complex reasoning tasks. Because of their extensive parameters and memory consumption, both Parameter-Efficient Fine-Tuning (PEFT) methods and Memory-Efficient Fine-Tuning methods have been proposed for LLMs. Nevertheless, the issue of large annotated data consumption, the aim of Data-Efficient Fine-Tuning, remains unexplored. One obvious way is to combine the PEFT method with active learning. However, the experimental results show that such a combination is not trivial and yields inferior results. Through probe experiments, such observation might be explained by two main reasons: uncertainty gap and poor model calibration. Therefore, in this paper, we propose a novel approach to effectively integrate uncertainty-based active learning and LoRA. Specifically, for the uncertainty gap, we introduce a dynamic uncertainty measurement that combines the uncertainty of the base model and the uncertainty of the full model during the iteration of active learning. For poor model calibration, we incorporate the regularization method during LoRA training to keep the model from being over-confident, and the Monte-Carlo dropout mechanism is employed to enhance the uncertainty estimation. Experimental results show that the proposed approach outperforms existing baseline models on three complex reasoning tasks.","url_abs":"https://arxiv.org/abs/2403.01165v2","url_pdf":"https://arxiv.org/pdf/2403.01165v2.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":"star-constraint-lora-with-dynamic-active","repo_url":"https://github.com/callanwu/star","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.01165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01165"}},"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/callanwu/star","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran":1,"unverified":5},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"6d89eb39c2cd1646","entry":"compute_accuracy","repo":"callanwu/star","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/callanwu/star/blob/HEAD/src/utils.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6d89eb39c2cd1646"}},{"code_sha256_prefix":"3ae892af2bb58706","entry":"normalize_list","repo":"callanwu/star","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/callanwu/star/blob/HEAD/src/utils.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":"3ae892af2bb58706"}},{"code_sha256_prefix":"a66989ce6d92af48","entry":"PE_dynamic_get_value","repo":"callanwu/star","repo_kind":"official","path":"src/al_methods.py","file_url":"https://github.com/callanwu/star/blob/HEAD/src/al_methods.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a66989ce6d92af48"}},{"code_sha256_prefix":"5349452625ae16c4","entry":"PE_get_value","repo":"callanwu/star","repo_kind":"official","path":"src/al_methods.py","file_url":"https://github.com/callanwu/star/blob/HEAD/src/al_methods.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5349452625ae16c4"}},{"code_sha256_prefix":"eb7884405cdeb0d4","entry":"PE_subtract_get_value","repo":"callanwu/star","repo_kind":"official","path":"src/al_methods.py","file_url":"https://github.com/callanwu/star/blob/HEAD/src/al_methods.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eb7884405cdeb0d4"}},{"code_sha256_prefix":"b5fa3dd31bc0ce52","entry":"extract_answer_number","repo":"callanwu/star","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/callanwu/star/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b5fa3dd31bc0ce52"}},{"code_sha256_prefix":"81d3d03f399b9a53","entry":"train","repo":"callanwu/star","repo_kind":"official","path":"src/finetuning.py","file_url":"https://github.com/callanwu/star/blob/HEAD/src/finetuning.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"81d3d03f399b9a53"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}