{"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/calibrated-language-model-fine-tuning-for-in","title":"Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data","arxiv_id":"2010.11506","date":"2020-10-22","proceeding":"EMNLP 2020 11","authors":["Lingkai Kong","Haoming Jiang","Yuchen Zhuang","Jie Lyu","Tuo Zhao","Chao Zhang"],"abstract":"Fine-tuned pre-trained language models can suffer from severe miscalibration for both in-distribution and out-of-distribution (OOD) data due to over-parameterization. To mitigate this issue, we propose a regularized fine-tuning method. Our method introduces two types of regularization for better calibration: (1) On-manifold regularization, which generates pseudo on-manifold samples through interpolation within the data manifold. Augmented training with these pseudo samples imposes a smoothness regularization to improve in-distribution calibration. (2) Off-manifold regularization, which encourages the model to output uniform distributions for pseudo off-manifold samples to address the over-confidence issue for OOD data. Our experiments demonstrate that the proposed method outperforms existing calibration methods for text classification in terms of expectation calibration error, misclassification detection, and OOD detection on six datasets. Our code can be found at https://github.com/Lingkai-Kong/Calibrated-BERT-Fine-Tuning.","url_abs":"https://arxiv.org/abs/2010.11506v1","url_pdf":"https://arxiv.org/pdf/2010.11506v1.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":"calibrated-language-model-fine-tuning-for-in","repo_url":"https://github.com/Lingkai-Kong/Calibrated-BERT-Fine-Tuning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"ood-detection","task_name":"Out of Distribution (OOD) Detection"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.11506","atlas_url":"https://app.syntology.ai/?focus=2010.11506","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}