{"id":"W4386942346","doi":"10.1145/3624918.3625336","title":"Retrieving Supporting Evidence for Generative Question Answering","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Question answering; Computer science; Statement (logic); Hallucinating; Information retrieval; Pipeline (software); Natural language processing; Questions and answers; Artificial intelligence; Domain (mathematical analysis); Linguistics; Programming language","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":[0.008665595,0.001417944,0.0009599128,0.003703984,0.0008232932,0.003151297,0.002618443,0.002792542,0.01102898],"category_scores_gemma":[0.08886425,0.0007643008,0.001590032,0.001168794,0.00208918,0.006036039,0.004700678,0.002318102,0.003671237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001174268,"about_ca_system_score_gemma":0.001653245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001682773,"about_ca_topic_score_gemma":0.003626524,"domain_scores_codex":[0.9904957,0.005202154,0.0005786091,0.001304871,0.002098337,0.0003204355],"domain_scores_gemma":[0.9342041,0.05226269,0.002177677,0.00686863,0.003838681,0.000648335],"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":[0.001456225,0.0009132455,0.03304749,0.004495662,0.0005016726,0.003969065,0.007394993,0.05634974,0.07395045,0.1036154,0.04649729,0.6678088],"study_design_scores_gemma":[0.0003426519,0.000360104,0.007668428,0.0005729027,0.0002546408,0.001487297,0.001639308,0.7477907,0.05013368,0.1492436,0.04036129,0.0001454228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2172464,0.001713888,0.7363096,0.005599395,0.0003207618,0.000778504,0.004372811,0.02140522,0.0122535],"genre_scores_gemma":[0.6914133,0.0002955322,0.2943428,0.0008476123,0.0002371895,0.0003100656,0.009718957,0.0008008286,0.002033711],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01102898,"threshold_uncertainty_score":0.04582858,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2230135931799158,"score_gpt":0.4047392601166221,"score_spread":0.1817256669367063,"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."}}