{"id":"W4412158322","doi":"10.1162/coli.a.16","title":"🧜Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models","year":2025,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":142,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Waterloo","funders":"","keywords":"Siren (mythology); Computer science; Natural language processing; Linguistics; Art; Literature; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005140209,0.0008492813,0.001062743,0.002366817,0.0004934295,0.003175358,0.001597508,0.001148357,0.001586639],"category_scores_gemma":[0.02783582,0.0005104649,0.0007931922,0.002056405,0.001366952,0.00486848,0.002398461,0.002218206,0.0006971562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007739268,"about_ca_system_score_gemma":0.001334841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003482481,"about_ca_topic_score_gemma":0.002808019,"domain_scores_codex":[0.9969144,0.001713533,0.0002364757,0.0003217274,0.0007179247,0.00009593038],"domain_scores_gemma":[0.9686005,0.02639811,0.0008496669,0.001659123,0.002112498,0.0003800677],"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":[0.0002802013,0.0002414738,0.01377635,0.003667572,0.0004307674,0.0005135548,0.00196258,0.06499913,0.00274424,0.03821485,0.01815425,0.855015],"study_design_scores_gemma":[0.00006028948,0.0004775016,0.006248761,0.002505156,0.0002659835,0.001388733,0.002371172,0.6917969,0.006658549,0.1558374,0.1321883,0.0002012651],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.06632197,0.2767638,0.6189047,0.0129323,0.0006774334,0.0003226401,0.0007851623,0.003878175,0.01941385],"genre_scores_gemma":[0.6460825,0.1689519,0.1725573,0.00301514,0.002313291,0.0002680934,0.002259748,0.0009694088,0.003582634],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.005140209,"threshold_uncertainty_score":0.02718437,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02578220776824297,"score_gpt":0.3496665190830933,"score_spread":0.3238843113148503,"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."}}