{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001892251,0.0001593888,0.0002798874,0.0004515667,0.0001458508,0.0003750286,0.0007729272,0.00004205698,3.746971e-8],"category_scores_gemma":[0.00007668306,0.00009589778,0.00003954547,0.001875413,0.0001245028,0.0005114709,0.0002736937,0.0002397642,1.301309e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007261849,"about_ca_system_score_gemma":0.0001077606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001133532,"about_ca_topic_score_gemma":0.000001014855,"domain_scores_codex":[0.9983987,0.00002958621,0.000361598,0.0004074873,0.0004398019,0.0003628521],"domain_scores_gemma":[0.999218,0.0002579823,0.0001163007,0.0001900246,0.0001221349,0.00009556126],"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":[0.0003017751,0.0001212193,0.002563383,0.002111616,0.00009432621,0.00001899162,0.008286866,0.5362516,0.06307205,0.3823348,0.0003780187,0.00446535],"study_design_scores_gemma":[0.0001356107,0.0001380649,0.0006889612,0.001273902,0.000005731298,0.00007019078,0.00004645314,0.9952754,0.002189669,0.00001889401,0.00004706883,0.000110011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9805171,0.002969197,0.01404476,0.00007808149,0.00187107,0.0003613333,0.000004077125,0.00007133577,0.00008306262],"genre_scores_gemma":[0.9994642,0.00002086037,0.0003090704,0.00001141726,0.0001091297,0.00001806715,6.262596e-8,0.000008038292,0.0000592187],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4590238,"threshold_uncertainty_score":0.3910598,"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."}}