{"id":"W2990557064","doi":"10.1609/aaai.v34i05.6328","title":"ALOHA: Artificial Learning of Human Attributes for Dialogue Agents","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"AI in Service Interactions","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Huawei Technologies","keywords":"Character (mathematics); Context (archaeology); Expression (computer science); Style (visual arts); Personality psychology; Space (punctuation); Language acquisition","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":[],"consensus_categories":[],"category_scores_codex":[0.0003881957,0.0002434688,0.0003838665,0.0001050272,0.0003333236,0.0001878489,0.002399293,0.00010807,0.0000732035],"category_scores_gemma":[0.001082839,0.0002063725,0.0002321101,0.0007184888,0.0002275815,0.0005098247,0.0005266158,0.000393466,0.00006552494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003789524,"about_ca_system_score_gemma":0.00008416815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005394517,"about_ca_topic_score_gemma":0.00001443937,"domain_scores_codex":[0.9977323,0.00002645555,0.0008462489,0.0005530751,0.0004719691,0.0003699289],"domain_scores_gemma":[0.9975227,0.0002431518,0.0007385281,0.0002528666,0.001115241,0.000127498],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006572851,0.0001497643,0.0004150839,0.00009567091,0.00003137269,3.204589e-7,0.003017321,0.0002597184,0.2205196,0.7627825,0.0004484726,0.01221451],"study_design_scores_gemma":[0.00003325406,0.0005912257,0.0001845294,0.0001539757,0.00002425645,0.00000134425,0.001027397,0.110607,0.7844906,0.1023722,0.0002911891,0.0002230204],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6419991,0.00002871617,0.3108321,0.03665344,0.001404544,0.001905675,0.00006167123,0.0003981047,0.006716673],"genre_scores_gemma":[0.9964754,0.000007468212,0.002806156,0.0003948266,0.0001794977,0.00004890817,0.000002848539,0.00001830668,0.00006658788],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6604102,"threshold_uncertainty_score":0.8415624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1921886413411311,"score_gpt":0.3437472161840571,"score_spread":0.151558574842926,"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."}}