{"id":"W7125770938","doi":"10.21428/594757db.d4fa15c1","title":"Conversation Alignment for Task-Oriented Dialogue Agents","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Queen's University","funders":"","keywords":"Conversation; Component (thermodynamics); Scope (computer science); Hyperparameter; Test (biology); Dialog system; Beam search","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":[0.01429932,0.001555205,0.001537104,0.001642264,0.002277803,0.003852813,0.003314964,0.002166149,0.00641844],"category_scores_gemma":[0.07429349,0.001188558,0.001155137,0.0006759971,0.002053766,0.005385316,0.006072015,0.00275924,0.002870184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001393864,"about_ca_system_score_gemma":0.003180906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003836439,"about_ca_topic_score_gemma":0.00318528,"domain_scores_codex":[0.9814324,0.01068497,0.001364009,0.002398701,0.003419648,0.0007001683],"domain_scores_gemma":[0.9589922,0.02563225,0.002803991,0.00479371,0.006311567,0.001466329],"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":[0.002704925,0.0009181681,0.01386284,0.001277709,0.0003093194,0.0009515668,0.01580553,0.09518057,0.08441236,0.04558696,0.01212597,0.7268641],"study_design_scores_gemma":[0.0001270572,0.0004871294,0.001520912,0.0001335371,0.00007343879,0.0004005955,0.001498496,0.89413,0.04224997,0.0434014,0.01581819,0.0001592172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03731636,0.0002085163,0.9422691,0.0002892561,0.00007069312,0.0004604612,0.0001600602,0.01659808,0.002627444],"genre_scores_gemma":[0.401941,0.00007494163,0.5933712,0.0002685711,0.00004123919,0.000655405,0.000496696,0.001357542,0.001793394],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01429932,"threshold_uncertainty_score":0.07562292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02180640931892866,"score_gpt":0.2636772030765954,"score_spread":0.2418707937576668,"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."}}