{"id":"W4385571455","doi":"10.18653/v1/2023.findings-acl.150","title":"Attribute Controlled Dialogue Prompting","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); Vector Institute","funders":"Vector Institute; University of Waterloo; Government of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Conversation; Task (project management); Domain (mathematical analysis); Open domain; Code (set theory); Artificial intelligence; Control (management); Natural language processing; Language model; Human–computer interaction; Machine learning; Programming language; Question answering; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0004302833,0.00006144059,0.0001394321,0.00006774288,0.00007438161,0.00009113127,0.0004375939,0.00002698445,0.00001492273],"category_scores_gemma":[0.0001070138,0.00004821895,0.00004879091,0.0003181412,0.000006626814,0.000174368,0.0002411615,0.00005619297,0.0005178341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001242321,"about_ca_system_score_gemma":0.00002763107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002232393,"about_ca_topic_score_gemma":0.000006411258,"domain_scores_codex":[0.9991919,0.00002984402,0.0001603435,0.000226855,0.0001525607,0.0002385212],"domain_scores_gemma":[0.9994423,0.0001225168,0.0000313981,0.0003232936,0.00003327351,0.00004717547],"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":[0.00002481246,0.00007317889,0.007912179,0.00004350861,0.0001107589,0.0001827003,0.002474946,0.01176532,0.00647524,0.7984508,0.01846279,0.1540238],"study_design_scores_gemma":[0.001309609,0.00001367917,0.001133008,0.000006040313,0.000001918761,0.000003035229,0.00001655852,0.9914645,0.000388932,0.004078737,0.001479976,0.0001039919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04558685,0.00001381724,0.9435971,0.002934258,0.0004058292,0.0002138042,4.256322e-7,0.001105509,0.006142426],"genre_scores_gemma":[0.9700594,0.000002896618,0.02595269,0.0003101625,0.0001074752,0.00003286171,0.000002025341,0.000004558553,0.003527907],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9796992,"threshold_uncertainty_score":0.6655883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0452125048558184,"score_gpt":0.2669467549645016,"score_spread":0.2217342501086832,"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."}}