{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005230551,0.000959516,0.0007894047,0.001502626,0.001178892,0.005508485,0.002137897,0.001919004,0.006594887],"category_scores_gemma":[0.03968281,0.00144778,0.0009514495,0.0007912962,0.004152685,0.01242985,0.004810414,0.003468257,0.002042684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001156765,"about_ca_system_score_gemma":0.0009113841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001165883,"about_ca_topic_score_gemma":0.002053569,"domain_scores_codex":[0.9944943,0.002873007,0.000314997,0.001003724,0.001156079,0.000157859],"domain_scores_gemma":[0.9759311,0.01699507,0.001161735,0.004162789,0.001286741,0.0004624987],"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":[0.00009704194,0.00006337203,0.001645962,0.0003137925,0.0001007826,0.0004507991,0.004210213,0.03210255,0.003185777,0.9163911,0.006567238,0.03487132],"study_design_scores_gemma":[0.00002740914,0.00003107509,0.0001756712,0.00005409105,0.00003942413,0.0001896676,0.000427812,0.1233794,0.001501056,0.8507382,0.02340938,0.00002690644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03086044,0.0008115891,0.940667,0.005045116,0.0001159983,0.0001450978,0.0006230831,0.002080394,0.01965123],"genre_scores_gemma":[0.5382479,0.001032024,0.4341062,0.001673493,0.0003073456,0.0007547648,0.002139001,0.001408647,0.02033068],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006594887,"threshold_uncertainty_score":0.0276621,"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."}}