{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002241003,0.0008553377,0.0008566447,0.0005813758,0.0004748002,0.0009186481,0.001536349,0.001471251,0.00770278],"category_scores_gemma":[0.01527643,0.0005609677,0.0004748348,0.0004866199,0.0007131558,0.001827384,0.001357849,0.002113758,0.001259589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00108039,"about_ca_system_score_gemma":0.002240194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006269207,"about_ca_topic_score_gemma":0.01058503,"domain_scores_codex":[0.9988978,0.0005897193,0.00005259615,0.0002231382,0.0001587249,0.00007800364],"domain_scores_gemma":[0.9933031,0.005556711,0.0001822863,0.0003270005,0.0004065801,0.0002242725],"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":[0.0009893903,0.0003754034,0.003153474,0.0004077141,0.00008414762,0.00017484,0.0006362834,0.7925472,0.005045313,0.01889019,0.007236002,0.17046],"study_design_scores_gemma":[0.00003206115,0.00003057284,0.00009600224,0.000007657226,0.000005490899,0.000009334706,0.0000191645,0.9940883,0.0005949116,0.004568889,0.0005425599,0.000005144712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04851085,0.000436073,0.9380215,0.0004657386,0.0001193118,0.0001765495,0.0002628774,0.007611136,0.004396005],"genre_scores_gemma":[0.7392115,0.0001196412,0.2568699,0.0002829857,0.00003890707,0.0003295043,0.0005526246,0.0005168513,0.002078107],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00770278,"threshold_uncertainty_score":0.02576834,"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."}}