{"id":"W7126410033","doi":"10.21428/594757db.1c863f43","title":"Large Language Models are Incoherent Storytellers","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Variety (cybernetics); Narrative; Natural language; Natural language generation; Natural (archaeology); Language planning; Range (aeronautics)","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":[0.000166352,0.00007427064,0.00007119942,0.00006701997,0.00003592802,0.0001416176,0.0004157915,0.00003276682,0.000128207],"category_scores_gemma":[0.000004560203,0.00006039188,0.00004364565,0.0001336354,0.00000553393,0.0003749712,0.00021806,0.0001005953,0.0001992416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004561504,"about_ca_system_score_gemma":0.00003879933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003986256,"about_ca_topic_score_gemma":0.00006719268,"domain_scores_codex":[0.9992193,0.00001908748,0.00009669915,0.0002850246,0.0001679228,0.000211968],"domain_scores_gemma":[0.9995036,0.00002580668,0.0000112324,0.0003835822,0.00001291254,0.00006282601],"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":[0.000001009745,0.00005369524,0.00008939859,0.00007926899,0.00003326241,0.0002134976,0.01266915,0.01215206,0.0003018521,0.9018711,0.0262357,0.04629994],"study_design_scores_gemma":[0.00005267069,0.000005485429,0.0000134774,0.00002460079,0.00000146361,0.000003776714,0.0003470397,0.9866675,0.0001780888,0.004758144,0.007860103,0.00008769667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01494866,0.0009007528,0.9600952,0.0008708604,0.0005178404,0.00006380089,0.000001507056,0.0005968857,0.02200449],"genre_scores_gemma":[0.9709225,0.00000869537,0.02320701,0.0004328221,0.00008132588,0.000006610964,6.400048e-7,0.00000737322,0.005333047],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9745154,"threshold_uncertainty_score":0.2560914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02472307406622115,"score_gpt":0.2581021526382649,"score_spread":0.2333790785720438,"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."}}