{"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/understanding-factuality-in-abstractive","title":"Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics","arxiv_id":"2104.13346","date":"2021-04-27","proceeding":"NAACL 2021 4","authors":["Artidoro Pagnoni","Vidhisha Balachandran","Yulia Tsvetkov"],"abstract":"Modern summarization models generate highly fluent but often factually unreliable outputs. This motivated a surge of metrics attempting to measure the factuality of automatically generated summaries. Due to the lack of common benchmarks, these metrics cannot be compared. Moreover, all these methods treat factuality as a binary concept and fail to provide deeper insights into the kinds of inconsistencies made by different systems. To address these limitations, we devise a typology of factual errors and use it to collect human annotations of generated summaries from state-of-the-art summarization systems for the CNN/DM and XSum datasets. Through these annotations, we identify the proportion of different categories of factual errors in various summarization models and benchmark factuality metrics, showing their correlation with human judgment as well as their specific strengths and weaknesses.","url_abs":"https://arxiv.org/abs/2104.13346v2","url_pdf":"https://arxiv.org/pdf/2104.13346v2.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":"understanding-factuality-in-abstractive","repo_url":"https://github.com/artidoro/frank","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"understanding-factuality-in-abstractive","repo_url":"https://github.com/bunsenfeng/factkb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2104.13346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.13346"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/artidoro/frank","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bunsenfeng/factkb","reach":{"status":"ok"}}],"summary":{"ran_honours":2,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2ec3c56451c218fd","entry":"human_metric_correlation","repo":"artidoro/frank","repo_kind":"official","path":"evaluation/evaluate.py","file_url":"https://github.com/artidoro/frank/blob/HEAD/evaluation/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2ec3c56451c218fd"}},{"code_sha256_prefix":"727187d8199941aa","entry":"parse_args","repo":"artidoro/frank","repo_kind":"official","path":"evaluation/evaluate.py","file_url":"https://github.com/artidoro/frank/blob/HEAD/evaluation/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"727187d8199941aa"}},{"code_sha256_prefix":"00f000efebe2b132","entry":"williams_test","repo":"artidoro/frank","repo_kind":"official","path":"evaluation/evaluate.py","file_url":"https://github.com/artidoro/frank/blob/HEAD/evaluation/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00f000efebe2b132"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}