{"id":"W4399364455","doi":"10.1145/3630106.3658993","title":"A Robot Walks into a Bar: Can Language Models Serve as Creativity SupportTools for Comedy? An Evaluation of LLMs’ Humour Alignment with Comedians","year":2024,"lang":"en","type":"article","venue":"","topic":"Humor Studies and Applications","field":"Psychology","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada)","funders":"","keywords":"Comedy; Creativity; Offensive; Sociology; Value (mathematics); Censorship; Media studies; Psychology; Visual arts; Computer science; Law; Engineering; Social psychology; Political science; Art","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006819718,0.0001633928,0.000260666,0.00006977796,0.0001048252,0.00003285558,0.0001442083,0.00006476224,0.0015238],"category_scores_gemma":[0.00001158261,0.0001251953,0.0000739489,0.0001580417,0.00007890163,0.00005978222,0.00003416197,0.00008652774,0.00003598248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001132576,"about_ca_system_score_gemma":0.0001228456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004176578,"about_ca_topic_score_gemma":0.007735577,"domain_scores_codex":[0.9986402,0.0001046062,0.000268963,0.0003905155,0.0003456172,0.0002500853],"domain_scores_gemma":[0.9991186,0.0001478109,0.00006595926,0.0004204692,0.0001370546,0.0001101141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003187901,0.002427817,0.002448783,0.0004940448,0.001763007,0.00004516418,0.3323454,0.00445345,0.01112599,0.55122,0.02175497,0.07160261],"study_design_scores_gemma":[0.01559825,0.009902835,0.03236638,0.0006249712,0.004804761,0.0001620841,0.5197986,0.2841455,0.01993762,0.08779929,0.02163185,0.003227903],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.928393,0.0004137929,0.02559783,0.004484964,0.0001504881,0.002482538,0.0003806906,0.0001722553,0.03792442],"genre_scores_gemma":[0.9931021,0.000005813692,0.002094146,0.0001970367,0.00007475544,0.001876405,0.0002416471,0.00003258405,0.00237546],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4634207,"threshold_uncertainty_score":0.9993889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0760012151814271,"score_gpt":0.4138802537248433,"score_spread":0.3378790385434162,"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."}}