{"id":"W2770550542","doi":"10.1145/3278721.3278777","title":"Ethical Challenges in Data-Driven Dialogue Systems","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; McGill University","funders":"","keywords":"Offensive; Adversarial system; Conversation; Computer science; Process (computing); Reinforcement learning; Data science; Artificial intelligence; Psychology; Communication; Operations research; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001407052,0.0002089116,0.0003784295,0.0001398583,0.00002845916,0.0002288359,0.005154795,0.0008385124,0.000007524388],"category_scores_gemma":[0.0001334331,0.0001845106,0.0000375423,0.00006617008,0.00004419545,0.000159595,0.01147041,0.001386261,0.0001098198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006852062,"about_ca_system_score_gemma":0.000205747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006543153,"about_ca_topic_score_gemma":0.000628703,"domain_scores_codex":[0.997268,0.0002943557,0.0004173681,0.001335209,0.0003848242,0.0003002903],"domain_scores_gemma":[0.9954689,0.0001683168,0.0001091865,0.004094462,0.0000725663,0.00008655684],"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":[0.000004401259,0.0001239176,0.0003116814,0.000973462,0.00007995307,0.0001401716,0.004169639,0.02906778,0.00001089182,0.9180908,0.005829826,0.04119748],"study_design_scores_gemma":[0.00009131439,0.000009898219,0.0001736558,0.0001841345,0.000003054474,0.000007347411,0.00002456035,0.9855531,0.000003470819,0.008368106,0.005344726,0.000236586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008517795,0.00187157,0.9684599,0.01186651,0.004155517,0.0003969478,0.00001785248,0.0003589515,0.01202096],"genre_scores_gemma":[0.8296554,0.001606511,0.165954,0.0004988534,0.001744783,0.00008844684,0.00009945319,0.00002999804,0.0003225268],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9564854,"threshold_uncertainty_score":0.9965246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2499743974985727,"score_gpt":0.3419228259791348,"score_spread":0.09194842848056209,"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."}}