{"id":"W4391335180","doi":"10.1145/3610977.3634999","title":"Generative Expressive Robot Behaviors using Large Language Models","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Robot; Human–computer interaction; Leverage (statistics); Motion (physics); Generative model; Generative grammar; Natural language; Context (archaeology); Artificial intelligence; Social robot; Mobile robot; Robot control","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002225986,0.000368924,0.0003178945,0.0002252568,0.0001650171,0.0005592474,0.001529942,0.000266717,0.00006854277],"category_scores_gemma":[0.00001831483,0.0003364511,0.0001809695,0.0002549922,0.00003145698,0.0001748598,0.00631549,0.001305153,0.0001591964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001525401,"about_ca_system_score_gemma":0.0002319983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002330145,"about_ca_topic_score_gemma":0.00004479495,"domain_scores_codex":[0.9976587,0.0001296504,0.0003264936,0.001146041,0.0003565332,0.0003825848],"domain_scores_gemma":[0.9980407,0.00005617844,0.000168752,0.001491782,0.0001104967,0.0001320763],"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":[0.000001204706,0.000134683,0.0000625421,0.00008606923,0.00007029644,0.00006614638,0.01113572,0.7965993,0.01349093,0.1742991,0.000487061,0.003566853],"study_design_scores_gemma":[0.00008390247,0.000007213174,0.00008275703,0.00008439511,0.00003647068,0.000008302399,0.00008682143,0.971046,0.002721176,0.02544173,0.00003107357,0.0003701379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0899788,0.0005246359,0.9031379,0.0007056296,0.0004549642,0.0005084177,0.00006262927,0.0008547187,0.003772315],"genre_scores_gemma":[0.6209808,0.000003984225,0.3778089,0.0001533045,0.0001377796,0.0001560705,0.00003610191,0.00003375957,0.0006893273],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.531002,"threshold_uncertainty_score":0.9999087,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03655862504537216,"score_gpt":0.3494611117712703,"score_spread":0.3129024867258982,"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."}}