{"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/generalization-in-nli-ways-not-to-go-beyond","title":"Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics","arxiv_id":"2110.01518","date":"2021-10-04","proceeding":"EMNLP (insights) 2021 11","authors":["Prajjwal Bhargava","Aleksandr Drozd","Anna Rogers"],"abstract":"Much of recent progress in NLU was shown to be due to models' learning dataset-specific heuristics. We conduct a case study of generalization in NLI (from MNLI to the adversarially constructed HANS dataset) in a range of BERT-based architectures (adapters, Siamese Transformers, HEX debiasing), as well as with subsampling the data and increasing the model size. We report 2 successful and 3 unsuccessful strategies, all providing insights into how Transformer-based models learn to generalize.","url_abs":"https://arxiv.org/abs/2110.01518v1","url_pdf":"https://arxiv.org/pdf/2110.01518v1.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":"generalization-in-nli-ways-not-to-go-beyond","repo_url":"https://github.com/prajjwal1/generalize_lm_nli","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.01518","atlas_url":"https://app.syntology.ai/?focus=2110.01518","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}