{"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/fast-and-accurate-factual-inconsistency","title":"Fast and Accurate Factual Inconsistency Detection Over Long Documents","arxiv_id":"2310.13189","date":"2023-10-19","proceeding":null,"authors":["Barrett Martin Lattimer","Patrick Chen","Xinyuan Zhang","Yi Yang"],"abstract":"Generative AI models exhibit remarkable potential; however, hallucinations across various tasks present a significant challenge, particularly for longer inputs that current approaches struggle to address effectively. We introduce SCALE (Source Chunking Approach for Large-scale inconsistency Evaluation), a task-agnostic model for detecting factual inconsistencies using a novel chunking strategy. Specifically, SCALE is a Natural Language Inference (NLI) based model that uses large text chunks to condition over long texts. This approach achieves state-of-the-art performance in factual inconsistency detection for diverse tasks and long inputs. Additionally, we leverage the chunking mechanism and employ a novel algorithm to explain SCALE's decisions through relevant source sentence retrieval. Our evaluations reveal that SCALE outperforms existing methods on both standard benchmarks and a new long-form dialogue dataset ScreenEval we constructed. Moreover, SCALE surpasses competitive systems in efficiency and model explanation evaluations. We have released our code and data publicly to GitHub.","url_abs":"https://arxiv.org/abs/2310.13189v2","url_pdf":"https://arxiv.org/pdf/2310.13189v2.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":"fast-and-accurate-factual-inconsistency","repo_url":"https://github.com/asappresearch/scale-score","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"chunking","task_name":"Chunking"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-retrieval","task_name":"Sentence Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2310.13189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13189"}},"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/asappresearch/scale-score","reach":null}],"summary":{"ran":2,"unverified":7},"by_repo_kind":{"official":{"samples":9,"ran":2,"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":9,"samples":[{"code_sha256_prefix":"688e220c3f53cdd8","entry":"get_chunks","repo":"asappresearch/scale-score","repo_kind":"official","path":"scale_score/scorer.py","file_url":"https://github.com/asappresearch/scale-score/blob/HEAD/scale_score/scorer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"688e220c3f53cdd8"}},{"code_sha256_prefix":"dcb0869afc0e1627","entry":"get_retrieval_chunks","repo":"asappresearch/scale-score","repo_kind":"official","path":"scale_score/scorer.py","file_url":"https://github.com/asappresearch/scale-score/blob/HEAD/scale_score/scorer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dcb0869afc0e1627"}},{"code_sha256_prefix":"c6d3f18edfe25897","entry":"SCALEScorer","repo":"asappresearch/scale-score","repo_kind":"official","path":"scale_score/scorer.py","file_url":"https://github.com/asappresearch/scale-score/blob/HEAD/scale_score/scorer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c6d3f18edfe25897"}},{"code_sha256_prefix":"ac6c38d1784086ed","entry":"get_flan_T5_model","repo":"asappresearch/scale-score","repo_kind":"official","path":"scale_score/scorer.py","file_url":"https://github.com/asappresearch/scale-score/blob/HEAD/scale_score/scorer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ac6c38d1784086ed"}},{"code_sha256_prefix":"6a13e7a55f442d56","entry":"retrieve","repo":"asappresearch/scale-score","repo_kind":"official","path":"scale_score/scorer.py","file_url":"https://github.com/asappresearch/scale-score/blob/HEAD/scale_score/scorer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6a13e7a55f442d56"}},{"code_sha256_prefix":"5a2d9fad0871c136","entry":"run_model_chunks","repo":"asappresearch/scale-score","repo_kind":"official","path":"scale_score/scorer.py","file_url":"https://github.com/asappresearch/scale-score/blob/HEAD/scale_score/scorer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5a2d9fad0871c136"}},{"code_sha256_prefix":"c781ef9635e6359a","entry":"scale_retrieve","repo":"asappresearch/scale-score","repo_kind":"official","path":"scale_score/scorer.py","file_url":"https://github.com/asappresearch/scale-score/blob/HEAD/scale_score/scorer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c781ef9635e6359a"}},{"code_sha256_prefix":"fcd4da1ae15f5f03","entry":"scale_score","repo":"asappresearch/scale-score","repo_kind":"official","path":"scale_score/scorer.py","file_url":"https://github.com/asappresearch/scale-score/blob/HEAD/scale_score/scorer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fcd4da1ae15f5f03"}},{"code_sha256_prefix":"0d59d2ed3cc16146","entry":"score","repo":"asappresearch/scale-score","repo_kind":"official","path":"scale_score/scorer.py","file_url":"https://github.com/asappresearch/scale-score/blob/HEAD/scale_score/scorer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0d59d2ed3cc16146"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}