{"id":"W4400663124","doi":"10.54254/2755-2721/76/20240608","title":"A review of methods for alleviating hallucination issues in large language models","year":2024,"lang":"en","type":"review","venue":"Applied and Computational Engineering","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Milton District Hospital","funders":"","keywords":"Psychology; Computer science; Linguistics; 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":[0.0008790761,0.0001763745,0.000641937,0.0001794273,0.00001902835,0.00003807905,0.000212592,0.00008207597,7.5675e-7],"category_scores_gemma":[0.00005175592,0.000157841,0.0001061313,0.0003433822,0.000005745094,0.0001078238,0.00009475322,0.000137171,0.000001283516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004094974,"about_ca_system_score_gemma":0.00006226378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002749249,"about_ca_topic_score_gemma":3.271805e-7,"domain_scores_codex":[0.9989246,0.00003334797,0.0005071291,0.0003224487,0.00008643641,0.0001260444],"domain_scores_gemma":[0.9992014,0.0004471907,0.0001262193,0.0001586349,0.00004122931,0.00002535248],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[1.502252e-7,0.000009754374,5.705304e-9,0.08518486,0.00001732948,1.367546e-7,0.0001762398,0.003735394,0.000001019203,0.207141,0.00001243043,0.7037217],"study_design_scores_gemma":[0.00006943286,0.000007882169,8.853671e-7,0.02566669,0.00007325201,0.000005168918,0.000006380975,0.8287368,6.736884e-7,0.006471451,0.1387838,0.0001776388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[9.852523e-8,0.5088325,0.4907283,0.0000231572,0.00002466443,0.0003262867,0.000006966939,0.00003370699,0.00002438532],"genre_scores_gemma":[0.00002751564,0.6650732,0.3345787,0.00002462212,0.00002117853,0.0001830549,0.0000762269,0.00001132769,0.000004206469],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8250014,"threshold_uncertainty_score":0.643657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04260581369658373,"score_gpt":0.3892562671185863,"score_spread":0.3466504534220026,"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."}}