{"id":"W4385570371","doi":"10.18653/v1/2023.findings-acl.29","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Bank of Canada; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Automatic summarization; Benchmark (surveying); Computer science; Variety (cybernetics); Strengths and weaknesses; Artificial intelligence; Machine translation; Machine learning; Data science; Benchmarking; Generative grammar; Ground truth; Natural language processing","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009656479,0.0000585918,0.0001501501,0.0001054221,0.00003420078,0.00003235421,0.0002364649,0.00001344904,0.000006748416],"category_scores_gemma":[0.00008410175,0.00004534888,0.00001159032,0.0002332604,0.000007452557,0.0001204924,0.0001889867,0.00002875214,0.00002500375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001357424,"about_ca_system_score_gemma":0.00002014986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003215129,"about_ca_topic_score_gemma":0.0000105404,"domain_scores_codex":[0.9987732,0.0001957548,0.0002046241,0.0002202455,0.0005238918,0.00008229765],"domain_scores_gemma":[0.9991131,0.0001751515,0.00006393441,0.0005304282,0.00009174216,0.00002563985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008632329,0.004368135,0.01630931,0.05598972,0.002287533,0.0002363514,0.1556054,0.1465128,0.005956397,0.3863467,0.02698109,0.1993202],"study_design_scores_gemma":[0.0003394663,0.00009839686,0.005325616,0.0002660016,0.00002266902,0.000001688249,0.0007176777,0.9923475,0.00004964826,0.0007755719,0.000002999416,0.00005278015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9720809,0.00007195667,0.02555093,0.0001455342,0.0001795224,0.001332782,0.000006221571,0.00009600432,0.0005361578],"genre_scores_gemma":[0.9989547,0.000001759994,0.0009270947,0.00004423193,0.000007352667,0.00003448094,0.000007622726,0.000002009892,0.00002071785],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8458347,"threshold_uncertainty_score":0.1849273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09181622296375748,"score_gpt":0.3453522069405535,"score_spread":0.2535359839767961,"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."}}