{"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/evaluating-groundedness-in-dialogue-systems","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","arxiv_id":"2105.00071","date":"2021-04-30","proceeding":null,"authors":["Nouha Dziri","Hannah Rashkin","Tal Linzen","David Reitter"],"abstract":"Knowledge-grounded dialogue systems powered by large language models often generate responses that, while fluent, are not attributable to a relevant source of information. Progress towards models that do not exhibit this issue requires evaluation metrics that can quantify its prevalence. To this end, we introduce the Benchmark for Evaluation of Grounded INteraction (BEGIN), comprised of 12k dialogue turns generated by neural dialogue systems trained on three knowledge-grounded dialogue corpora. We collect human annotations assessing the extent to which the models' responses can be attributed to the given background information. We then use BEGIN to analyze eight evaluation metrics. We find that these metrics rely on spurious correlations, do not reliably distinguish attributable abstractive responses from unattributable ones, and perform substantially worse when the knowledge source is longer. Our findings underscore the need for more sophisticated and robust evaluation metrics for knowledge-grounded dialogue. We make BEGIN publicly available at https://github.com/google/BEGIN-dataset.","url_abs":"https://arxiv.org/abs/2105.00071v3","url_pdf":"https://arxiv.org/pdf/2105.00071v3.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":"evaluating-groundedness-in-dialogue-systems","repo_url":"https://github.com/google/BEGIN-dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"}],"methods":[],"datasets_introduced":[{"slug":"https-github-com-google-begin-dataset","name":"https://github.com/google/BEGIN-dataset","full_name":"BEGIN-Benchmark for Faithfulness"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.00071","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}