{"work":{"id":"9990d84d-84b4-4fd4-acb5-da451524d2f4","openalex_id":null,"doi":null,"arxiv_id":"1801.06146","raw_key":null,"title":"Universal Language Model Fine-tuning for Text Classification","authors":null,"authors_text":"Jeremy Howard and Sebastian Ruder","year":2018,"venue":"cs.CL","abstract":"Inductive transfer learning has greatly impacted computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch. We propose Universal Language Model Fine-tuning (ULMFiT), an effective transfer learning method that can be applied to any task in NLP, and introduce techniques that are key for fine-tuning a language model. Our method significantly outperforms the state-of-the-art on six text classification tasks, reducing the error by 18-24% on the majority of datasets. Furthermore, with only 100 labeled examples, it matches the performance of training from scratch on 100x more data. We open-source our pretrained models and code.","external_url":"https://arxiv.org/abs/1801.06146","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-07-04T07:39:38.353471+00:00","pith_arxiv_id":"1801.06146","created_at":"2026-05-09T04:47:44.433303+00:00","updated_at":"2026-07-04T07:39:38.353471+00:00","title_quality_ok":true,"display_title":"Universal Language Model Fine-tuning for Text Classification","render_title":"Universal Language Model Fine-tuning for Text Classification"},"hub":{"state":{"work_id":"9990d84d-84b4-4fd4-acb5-da451524d2f4","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":38,"external_cited_by_count":null,"distinct_field_count":9,"first_pith_cited_at":"2019-06-19T17:35:48+00:00","last_pith_cited_at":"2026-06-19T22:36:21+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T22:19:26.142775+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":5},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":5},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}