{"id":"W4402452666","doi":"10.11159/mhci24.104","title":"Reducing Response Delays in Dialogue Systems Using the Predictive Performance of Large Language Models","year":2024,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Language model; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003002179,0.001365592,0.0008011441,0.0005465213,0.0005587081,0.00132389,0.001157399,0.0011238,0.001448855],"category_scores_gemma":[0.02335685,0.0005070444,0.0003266605,0.0004127326,0.0005420418,0.002188407,0.001367898,0.001693156,0.0005435813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007079729,"about_ca_system_score_gemma":0.001324724,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005058726,"about_ca_topic_score_gemma":0.004981802,"domain_scores_codex":[0.9974563,0.001372775,0.0001033958,0.000345273,0.0005388287,0.0001833731],"domain_scores_gemma":[0.9831142,0.0137692,0.0008715321,0.0008015071,0.001173074,0.0002704418],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00366025,0.0008528393,0.00581348,0.0004562935,0.0001629075,0.0003959078,0.001466113,0.5047414,0.1476208,0.00454739,0.003047923,0.3272346],"study_design_scores_gemma":[0.00006891136,0.0004011681,0.001068488,0.00001333192,0.00004909936,0.00005473111,0.0001548756,0.9680359,0.02692827,0.002110334,0.00107594,0.00003893168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2076241,0.0006554625,0.7837484,0.0006431625,0.0001121174,0.0001584248,0.0001145988,0.005252521,0.001691138],"genre_scores_gemma":[0.9144073,0.000134753,0.08404108,0.00009412407,0.00005989883,0.0001068119,0.000108318,0.0001896661,0.0008579965],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005058726,"threshold_uncertainty_score":0.01587725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008956364262571213,"score_gpt":0.2203933985059813,"score_spread":0.2114370342434101,"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."}}