{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001507917,0.0001122507,0.0001340782,0.0002948351,0.0001015674,0.0001073693,0.0006095241,0.000062545,0.000002706703],"category_scores_gemma":[0.003504268,0.00009994808,0.00002362512,0.000710151,0.00001629712,0.00004315704,0.0001171469,0.0004466688,0.00000884303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001313822,"about_ca_system_score_gemma":0.0002328763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005339435,"about_ca_topic_score_gemma":0.0008635564,"domain_scores_codex":[0.9983162,0.0005008184,0.0003116855,0.0002973137,0.0003517386,0.0002221866],"domain_scores_gemma":[0.9976754,0.001657096,0.00007107719,0.0002762325,0.000295567,0.00002460444],"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":[0.000006341449,0.00007106833,0.02528556,0.00001713034,0.000001773444,0.00002082613,0.001660036,0.481504,2.47307e-8,0.4898525,0.0004173033,0.001163463],"study_design_scores_gemma":[0.0002317293,0.00002311933,0.2538013,0.00005113423,7.537183e-7,5.616411e-7,0.0000240142,0.7033906,2.863912e-7,0.0420378,0.0003756339,0.00006307061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02804944,0.0002163912,0.9579679,0.003560403,0.001026439,0.0004052241,0.00004531341,0.0001153448,0.008613486],"genre_scores_gemma":[0.9845143,0.000001727642,0.01208354,0.003111054,0.00009151656,0.000006391571,0.0001134191,0.000006146959,0.00007190397],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9564649,"threshold_uncertainty_score":0.4195189,"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."}}