{"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/large-language-models-perform-diagnostic","title":"Large Language Models Perform Diagnostic Reasoning","arxiv_id":"2307.08922","date":"2023-07-18","proceeding":null,"authors":["Cheng-Kuang Wu","Wei-Lin Chen","Hsin-Hsi Chen"],"abstract":"We explore the extension of chain-of-thought (CoT) prompting to medical reasoning for the task of automatic diagnosis. Motivated by doctors' underlying reasoning process, we present Diagnostic-Reasoning CoT (DR-CoT). Empirical results demonstrate that by simply prompting large language models trained only on general text corpus with two DR-CoT exemplars, the diagnostic accuracy improves by 15% comparing to standard prompting. Moreover, the gap reaches a pronounced 18% in out-domain settings. Our findings suggest expert-knowledge reasoning in large language models can be elicited through proper promptings.","url_abs":"https://arxiv.org/abs/2307.08922v1","url_pdf":"https://arxiv.org/pdf/2307.08922v1.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":"large-language-models-perform-diagnostic","repo_url":"https://github.com/nlplab-best-team/diagnostic-reasoning","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"medical-diagnosis","task_name":"Medical Diagnosis"}],"methods":[{"method_slug":"cot-prompting","method_name":"CoT Prompting"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.08922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08922"}},"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/nlplab-best-team/diagnostic-reasoning","reach":{"status":"ok"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"79d0b5c84865942b","entry":"calc_num_tokens","repo":"nlplab-best-team/diagnostic-reasoning","repo_kind":"official","path":"utils.py","file_url":"https://github.com/nlplab-best-team/diagnostic-reasoning/blob/HEAD/utils.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":"79d0b5c84865942b"}},{"code_sha256_prefix":"af8150846ef26adb","entry":"load_all_diagnoses","repo":"nlplab-best-team/diagnostic-reasoning","repo_kind":"official","path":"utils.py","file_url":"https://github.com/nlplab-best-team/diagnostic-reasoning/blob/HEAD/utils.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":"af8150846ef26adb"}},{"code_sha256_prefix":"a544b157dd386e5e","entry":"preprocess_data","repo":"nlplab-best-team/diagnostic-reasoning","repo_kind":"official","path":"eda/utils.py","file_url":"https://github.com/nlplab-best-team/diagnostic-reasoning/blob/HEAD/eda/utils.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":"a544b157dd386e5e"}},{"code_sha256_prefix":"ca44febbe40bbaab","entry":"read_pathology_data","repo":"nlplab-best-team/diagnostic-reasoning","repo_kind":"official","path":"eda/utils.py","file_url":"https://github.com/nlplab-best-team/diagnostic-reasoning/blob/HEAD/eda/utils.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":"ca44febbe40bbaab"}},{"code_sha256_prefix":"56c08282ee8295b4","entry":"read_patient_data","repo":"nlplab-best-team/diagnostic-reasoning","repo_kind":"official","path":"eda/utils.py","file_url":"https://github.com/nlplab-best-team/diagnostic-reasoning/blob/HEAD/eda/utils.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":"56c08282ee8295b4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}