{"id":"W4385572965","doi":"10.18653/v1/2022.emnlp-main.82","title":"Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Naval Information Warfare Center Pacific; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; Allen Institute for Artificial Intelligence","keywords":"Inference; Correctness; Computer science; Robustness (evolution); Commonsense reasoning; Artificial intelligence; Rule of inference; Machine learning; Natural language processing; Algorithm","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002138216,0.00007083748,0.00008123511,0.00005473325,0.0003254601,0.00007289509,0.0004639332,0.00001176209,0.0001480124],"category_scores_gemma":[0.00002779959,0.0000567503,0.0000230904,0.000223816,0.00001742234,0.0001275074,0.00033221,0.0001416131,0.00001036964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007510948,"about_ca_system_score_gemma":0.0000900741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002008179,"about_ca_topic_score_gemma":0.000009620127,"domain_scores_codex":[0.9990111,0.00006490403,0.0001292376,0.0003071747,0.0003008632,0.0001867066],"domain_scores_gemma":[0.9994369,0.00006011373,0.00005998152,0.0003340807,0.00005233016,0.00005659065],"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":[0.00000340102,0.00003779291,0.0006212599,0.000002438201,0.00001154574,0.00004051367,0.0006036788,0.008064312,0.00003180082,0.9880044,0.0002529089,0.002325979],"study_design_scores_gemma":[0.002044414,0.00139024,0.005635265,0.00009134376,0.00005161647,0.001569591,0.005865511,0.8495553,0.0004669367,0.08472681,0.04723638,0.001366635],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01742995,0.00003431204,0.9458951,0.003459735,0.00009771199,0.0001983281,9.45637e-7,0.0002221219,0.03266177],"genre_scores_gemma":[0.6614527,6.913526e-7,0.3365762,0.0006763056,0.00001129007,0.00006989481,0.000001953443,0.00000385223,0.001207161],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9032776,"threshold_uncertainty_score":0.2503209,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03000526500158486,"score_gpt":0.2339525538757103,"score_spread":0.2039472888741254,"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."}}