{"id":"W4408145959","doi":"10.1109/icmla61862.2024.00187","title":"Evaluating the Efficacy of Large Language Models in Automating Academic Peer Reviews","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Natural language processing","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02791481,0.001375934,0.0009026767,0.002389084,0.0006725134,0.003015382,0.001803487,0.001748914,0.001136469],"category_scores_gemma":[0.1088986,0.000610906,0.0009035643,0.00137267,0.0005562991,0.002800651,0.001483129,0.001588651,0.001301549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001588249,"about_ca_system_score_gemma":0.002426542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006699264,"about_ca_topic_score_gemma":0.009259839,"domain_scores_codex":[0.9828689,0.01207549,0.00130158,0.001968761,0.001525028,0.0002602407],"domain_scores_gemma":[0.8014678,0.1754998,0.006042127,0.007384837,0.008373608,0.001231792],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005083824,0.003044358,0.05560305,0.003315912,0.001436758,0.0005434569,0.002935502,0.3102587,0.02167998,0.003374625,0.01203209,0.5806918],"study_design_scores_gemma":[0.0002151424,0.0009177324,0.00551572,0.0000812455,0.0001627696,0.0001403488,0.0003162698,0.979936,0.007771839,0.001867058,0.003007591,0.00006823397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7672227,0.003587864,0.1980056,0.00170623,0.0004998156,0.001764612,0.002083874,0.01867874,0.006450602],"genre_scores_gemma":[0.8331898,0.0004566014,0.1619207,0.0003049138,0.0001268726,0.0004678179,0.001955094,0.0003348763,0.001243191],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9720852,"threshold_uncertainty_score":0.1476294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.131467812164552,"score_gpt":0.4317497698631278,"score_spread":0.3002819576985758,"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."}}