{"id":"W4409576534","doi":"10.61091/jcmcc127a-116","title":"An Optimization Study of Attention Mechanism-Based Natural Language Generation Models in Multi-Round Conversations","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Mechanism (biology); Natural language generation; Natural (archaeology); Natural language processing; Natural language; Artificial intelligence; History; Physics","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":[0.002921046,0.001327107,0.00101272,0.0005750807,0.0006392039,0.00107071,0.001637118,0.001224413,0.003089598],"category_scores_gemma":[0.006186777,0.0007400443,0.0008126845,0.0004360326,0.000602514,0.002171157,0.00127014,0.001376867,0.0005530809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001901791,"about_ca_system_score_gemma":0.001998777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008231912,"about_ca_topic_score_gemma":0.007198179,"domain_scores_codex":[0.9987088,0.0005291564,0.00005594506,0.0003426369,0.000180929,0.0001824982],"domain_scores_gemma":[0.997227,0.001992702,0.0001731692,0.0001489166,0.0003114787,0.0001466395],"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":[0.0002712852,0.0002127183,0.001545469,0.0001671601,0.00008160123,0.0001761115,0.0002779221,0.8823805,0.007064532,0.01128222,0.001814064,0.09472647],"study_design_scores_gemma":[0.000006542227,0.00003423867,0.000106592,0.000002157182,0.0000110087,0.00001439675,0.0000122482,0.997734,0.0005587079,0.001344301,0.0001715356,0.000004442649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0910901,0.0007643994,0.9023553,0.0004635558,0.00005767108,0.0002086912,0.00007791067,0.0009308938,0.004051595],"genre_scores_gemma":[0.8812784,0.0003047433,0.1134543,0.0001820313,0.00003674555,0.0002854345,0.0001555617,0.0001662987,0.004136505],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008231912,"threshold_uncertainty_score":0.01636797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02365745033667081,"score_gpt":0.2817597256151382,"score_spread":0.2581022752784674,"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."}}