{"id":"W4407423530","doi":"10.1016/j.enganabound.2025.106150","title":"Optimizing chatbot responsiveness: Automated history context selector via three-way decision for multi-turn dialogue Large Language Models","year":2025,"lang":"en","type":"article","venue":"Engineering Analysis with Boundary Elements","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"Science and Technology Service Network Plan; Key Science and Technology Program of Shaanxi Province; National Key Research and Development Program of China; National Natural Science Foundation of China; Department of Science and Technology of Sichuan Province; Organization Department of Sichuan Provincial Party Committee; Ministry of Science and Technology of the People's Republic of China","keywords":"Chatbot; Computer science; Context (archaeology); Language model; Turn-taking; Natural language processing; Artificial intelligence; Linguistics; Philosophy; History; Conversation","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007429849,0.0003226463,0.0005285505,0.0009167607,0.0002317627,0.0001726995,0.0007377368,0.0001013019,0.00001148697],"category_scores_gemma":[0.0000947892,0.0003040348,0.0002098852,0.00110039,0.00002048927,0.000521513,0.0002008828,0.0001933819,0.000003438078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006261259,"about_ca_system_score_gemma":0.0002243405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001481077,"about_ca_topic_score_gemma":0.0006255735,"domain_scores_codex":[0.9977425,0.00005257162,0.0005376426,0.0007190096,0.0003728957,0.0005753987],"domain_scores_gemma":[0.998507,0.0001938915,0.0001605217,0.0008217652,0.0002059126,0.0001109651],"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":[0.0001100117,0.0001461469,0.001206028,0.00008998868,0.002121922,0.0000344181,0.002454008,0.9743869,0.002369239,0.001838817,0.0002197068,0.01502279],"study_design_scores_gemma":[0.001338807,0.00004934163,0.000700623,0.0001065103,0.0002720797,0.000001307566,0.0000408431,0.9944825,0.0004007634,0.0000442354,0.002250687,0.0003122814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05006422,0.002135238,0.9462218,0.00004206025,0.0003780583,0.0003835734,0.00001983629,0.0007424253,0.00001280854],"genre_scores_gemma":[0.6662133,0.000006702182,0.3332306,0.0001349824,0.00002834915,0.0001075939,0.00004733509,0.00002399719,0.0002071041],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6161491,"threshold_uncertainty_score":0.9999412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01560009810235682,"score_gpt":0.2557725835512621,"score_spread":0.2401724854489053,"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."}}