{"id":"W4389519096","doi":"10.18653/v1/2023.emnlp-main.439","title":"Prompt-Based Monte-Carlo Tree Search for Goal-oriented Dialogue Policy Planning","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Atomic Energy of Canada Limited","keywords":"Monte Carlo tree search; Computer science; Task (project management); Tree (set theory); Machine learning; Artificial intelligence; Resource (disambiguation); Monte Carlo method; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.000430742,0.0001304985,0.0001543442,0.0003291422,0.000155954,0.0001122106,0.0006764665,0.00006325841,0.000004402702],"category_scores_gemma":[0.0001075624,0.0001164503,0.00008360877,0.0008541861,0.00002273523,0.0002129799,0.0002325636,0.000106015,0.00006172027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006779522,"about_ca_system_score_gemma":0.0002415749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004237037,"about_ca_topic_score_gemma":0.00003592322,"domain_scores_codex":[0.9984198,0.00004307628,0.0002185652,0.0004644028,0.0003049099,0.0005491978],"domain_scores_gemma":[0.99896,0.00022339,0.00003280341,0.0005624613,0.00009322781,0.0001280954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001052688,0.0002462201,0.0159739,0.0002889427,0.0001024477,0.0001239362,0.01004346,0.2975605,0.008169795,0.4479499,0.02058023,0.1988554],"study_design_scores_gemma":[0.0005963271,0.00007611972,0.002030345,0.00002132205,0.000002015112,0.000001215283,0.00006134022,0.9916593,0.002634521,0.0006405376,0.002128022,0.0001489499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08967355,0.00001289737,0.9021246,0.004541301,0.0002563672,0.000456078,0.000006987605,0.0008522322,0.002075989],"genre_scores_gemma":[0.9280743,7.477358e-7,0.06868189,0.000485424,0.0002828858,0.0001312692,0.00001179635,0.00001860258,0.002313086],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8384007,"threshold_uncertainty_score":0.4748705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05847833387990965,"score_gpt":0.3237633957141225,"score_spread":0.2652850618342129,"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."}}