{"id":"W4388142096","doi":"10.1371/journal.pdig.0000388","title":"Hallucination or Confabulation? Neuroanatomy as metaphor in Large Language Models","year":2023,"lang":"en","type":"article","venue":"PLOS Digital Health","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":73,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Confabulation (neural networks); Metaphor; Psychology; Cognitive psychology; Cognitive science; Linguistics; Cognition; Neuroscience; Philosophy","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":[0.000165778,0.00009513079,0.00014426,0.00009088185,0.00004620583,0.00003280395,0.0001043578,0.00009137097,0.00001504283],"category_scores_gemma":[0.0002457827,0.00007725057,0.00003222757,0.0002532809,0.00003228826,0.00001062483,0.00007280089,0.00007891221,0.0000592134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001839638,"about_ca_system_score_gemma":0.000146837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003533675,"about_ca_topic_score_gemma":0.0001237561,"domain_scores_codex":[0.9990535,0.00003743052,0.0002028706,0.0002537891,0.000153293,0.000299123],"domain_scores_gemma":[0.9996251,0.00003134564,0.0000541254,0.0001677136,0.00002765473,0.00009409569],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001533185,0.003318809,0.02506197,0.001434708,0.000428039,0.0006106336,0.009844258,0.001165792,0.01121761,0.008566804,0.03442232,0.9023958],"study_design_scores_gemma":[0.02400035,0.01344724,0.1523964,0.001046905,0.00009939712,0.0003007942,0.02427833,0.3215739,0.03004985,0.01848447,0.4096323,0.00468999],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9942061,0.0005426219,0.0005108711,0.001421053,0.00007052641,0.0002158007,0.00009664095,0.0001037723,0.002832642],"genre_scores_gemma":[0.9966942,0.0001349311,0.0001629565,0.0007645659,0.00004987732,0.00002030602,0.0004754935,0.00001539146,0.001682268],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8977059,"threshold_uncertainty_score":0.3150187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0338593488114151,"score_gpt":0.334673976730809,"score_spread":0.3008146279193939,"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."}}