{"id":"W4396624257","doi":"10.48550/arxiv.2405.00492","title":"Is Temperature the Creativity Parameter of Large Language Models?","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Creativity; Linguistics; Psychology; Philosophy; Social psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003057008,0.0002403777,0.0002794575,0.0001318165,0.00008247928,0.0001220556,0.001783828,0.0002664652,0.00002796531],"category_scores_gemma":[0.00002132136,0.0001928932,0.0002655358,0.0003923114,0.00006366299,0.0002017065,0.003495979,0.0008870473,0.00003208034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007345833,"about_ca_system_score_gemma":0.0001429651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002402075,"about_ca_topic_score_gemma":0.00003964348,"domain_scores_codex":[0.9984515,0.0001296284,0.0001628677,0.0008737585,0.0001177823,0.000264513],"domain_scores_gemma":[0.9978156,0.0001318828,0.0001278987,0.001769147,0.00008897534,0.0000665142],"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":[0.00001496645,0.0001167179,0.0005576955,0.0003496865,0.000266681,0.0003482358,0.008278386,0.2166958,0.0002131331,0.7710846,0.001348819,0.0007251998],"study_design_scores_gemma":[0.0001143303,0.00001085107,0.00006161656,0.0001025979,0.00005489278,0.000002301496,0.0001532692,0.8515099,0.0005303688,0.1471803,0.00009043613,0.0001891421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6311356,0.0003728422,0.3644168,0.0003880906,0.0003793455,0.0002086345,0.0000557702,0.0001473024,0.002895554],"genre_scores_gemma":[0.9950852,0.00005779718,0.001598021,0.0002462744,0.00006001097,8.917303e-7,0.000004211171,0.00001375173,0.002933787],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.634814,"threshold_uncertainty_score":0.7865956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06541205719938131,"score_gpt":0.2119207692218404,"score_spread":0.1465087120224591,"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."}}