{"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/this-is-not-correct-negation-aware-evaluation","title":"This is not correct! Negation-aware Evaluation of Language Generation Systems","arxiv_id":"2307.13989","date":"2023-07-26","proceeding":null,"authors":["Miriam Anschütz","Diego Miguel Lozano","Georg Groh"],"abstract":"Large language models underestimate the impact of negations on how much they change the meaning of a sentence. Therefore, learned evaluation metrics based on these models are insensitive to negations. In this paper, we propose NegBLEURT, a negation-aware version of the BLEURT evaluation metric. For that, we designed a rule-based sentence negation tool and used it to create the CANNOT negation evaluation dataset. Based on this dataset, we fine-tuned a sentence transformer and an evaluation metric to improve their negation sensitivity. Evaluating these models on existing benchmarks shows that our fine-tuned models outperform existing metrics on the negated sentences by far while preserving their base models' performances on other perturbations.","url_abs":"https://arxiv.org/abs/2307.13989v1","url_pdf":"https://arxiv.org/pdf/2307.13989v1.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":"this-is-not-correct-negation-aware-evaluation","repo_url":"https://github.com/MiriUll/negation_aware_evaluation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"this-is-not-correct-negation-aware-evaluation","repo_url":"https://github.com/dmlls/negate","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"embeddings-evaluation","task_name":"Embeddings Evaluation"},{"task_slug":"negation","task_name":"Negation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[{"slug":"cannot","name":"CANNOT","full_name":"Compilation of ANnotated, Negation-Oriented Text-pairs"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.13989","atlas_url":"https://app.syntology.ai/?focus=2307.13989","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}