{"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/fine-tuning-pre-trained-language-model-with","title":"Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach","arxiv_id":"2010.07835","date":"2020-10-15","proceeding":"NAACL 2021 4","authors":["Yue Yu","Simiao Zuo","Haoming Jiang","Wendi Ren","Tuo Zhao","Chao Zhang"],"abstract":"Fine-tuned pre-trained language models (LMs) have achieved enormous success in many natural language processing (NLP) tasks, but they still require excessive labeled data in the fine-tuning stage. We study the problem of fine-tuning pre-trained LMs using only weak supervision, without any labeled data. This problem is challenging because the high capacity of LMs makes them prone to overfitting the noisy labels generated by weak supervision. To address this problem, we develop a contrastive self-training framework, COSINE, to enable fine-tuning LMs with weak supervision. Underpinned by contrastive regularization and confidence-based reweighting, this contrastive self-training framework can gradually improve model fitting while effectively suppressing error propagation. Experiments on sequence, token, and sentence pair classification tasks show that our model outperforms the strongest baseline by large margins on 7 benchmarks in 6 tasks, and achieves competitive performance with fully-supervised fine-tuning methods.","url_abs":"https://arxiv.org/abs/2010.07835v3","url_pdf":"https://arxiv.org/pdf/2010.07835v3.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":"fine-tuning-pre-trained-language-model-with","repo_url":"https://github.com/yueyu1030/COSINE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-pair-classification","task_name":"Sentence-Pair Classification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"word-sense-disambiguation","task_name":"Word Sense Disambiguation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sentiment-analysis-on-imdb","task":"Sentiment Analysis","dataset":"IMDb","model":"COSINE","rank_in_archive_order":36,"of":49,"metrics":{"Accuracy":"90.54"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-yelp-2","task":"Text Classification","dataset":"Yelp-2","model":"COSINE","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"95.97%"},"uses_additional_data":false},{"leaderboard":"/sota/word-sense-disambiguation-on-words-in-context","task":"Word Sense Disambiguation","dataset":"Words in Context","model":"COSINE + Transductive Learning","rank_in_archive_order":1,"of":37,"metrics":{"Accuracy":"85.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.07835","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.07835"}},"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/yueyu1030/COSINE","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"643c03f907f7dc7c","entry":"compute_metrics","repo":"yueyu1030/COSINE","repo_kind":"official","path":"utils.py","file_url":"https://github.com/yueyu1030/COSINE/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"643c03f907f7dc7c"}},{"code_sha256_prefix":"d7682df458b2fe00","entry":"convert_examples_to_features_re","repo":"yueyu1030/COSINE","repo_kind":"official","path":"data_loader_new.py","file_url":"https://github.com/yueyu1030/COSINE/blob/HEAD/data_loader_new.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7682df458b2fe00"}},{"code_sha256_prefix":"0f7620720c0761a8","entry":"get_label","repo":"yueyu1030/COSINE","repo_kind":"official","path":"utils.py","file_url":"https://github.com/yueyu1030/COSINE/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f7620720c0761a8"}},{"code_sha256_prefix":"71e29a5bf54e04e7","entry":"tokenize_with_2span","repo":"yueyu1030/COSINE","repo_kind":"official","path":"data_loader_new.py","file_url":"https://github.com/yueyu1030/COSINE/blob/HEAD/data_loader_new.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"71e29a5bf54e04e7"}},{"code_sha256_prefix":"7ac17cb99fe26c74","entry":"tokenize_with_span","repo":"yueyu1030/COSINE","repo_kind":"official","path":"data_loader_new.py","file_url":"https://github.com/yueyu1030/COSINE/blob/HEAD/data_loader_new.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7ac17cb99fe26c74"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}