{"id":"W7140095476","doi":"10.1109/icaiqsa67794.2025.11440503","title":"AuditGPT: Automated Financial Auditing and Regulatory Compliance Checks using LLMs","year":2025,"lang":"","type":"article","venue":"","topic":"Auditing, Earnings Management, Governance","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Audit; Compliance (psychology); Financial Audit; Internal control; Government (linguistics)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003004427,0.001037322,0.0007668527,0.003184253,0.0006102087,0.002457694,0.00154144,0.001113659,0.004323395],"category_scores_gemma":[0.0176414,0.0004968411,0.00107518,0.001864936,0.000738215,0.00468439,0.003447124,0.00130545,0.003039067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008956024,"about_ca_system_score_gemma":0.002958453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006271278,"about_ca_topic_score_gemma":0.005809229,"domain_scores_codex":[0.9971349,0.001111354,0.0002744186,0.0004675721,0.000875144,0.0001365621],"domain_scores_gemma":[0.992747,0.00317597,0.0008415155,0.002012874,0.001041734,0.0001807603],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008243819,0.0003979782,0.008704012,0.0009150754,0.0002003261,0.0005981653,0.0008576455,0.02675151,0.01652705,0.01215806,0.08962004,0.8424457],"study_design_scores_gemma":[0.0002687277,0.0004394145,0.004672933,0.0002452922,0.0001679439,0.0007476097,0.0004757762,0.8220321,0.04752553,0.04308271,0.08013002,0.0002120357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04004207,0.001205743,0.6674019,0.001309156,0.0003248182,0.0009781197,0.008322565,0.2752393,0.005176242],"genre_scores_gemma":[0.3794209,0.000709837,0.5876375,0.0008328301,0.0001852833,0.0006063957,0.02192637,0.002864774,0.005815966],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006271278,"threshold_uncertainty_score":0.01588917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01693895228381571,"score_gpt":0.2494130777708226,"score_spread":0.2324741254870069,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}