{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002655141,0.001575493,0.00137379,0.002472433,0.0006464958,0.002390773,0.002321764,0.001471119,0.003852273],"category_scores_gemma":[0.01097639,0.0007856787,0.002017578,0.003107775,0.001032941,0.003808711,0.001502001,0.002650496,0.002424823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008212251,"about_ca_system_score_gemma":0.001604079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002942189,"about_ca_topic_score_gemma":0.002665148,"domain_scores_codex":[0.9981414,0.0005835333,0.0002997471,0.0003152225,0.0005919448,0.00006814089],"domain_scores_gemma":[0.9936248,0.004590648,0.0002818624,0.0004940813,0.0009207145,0.00008782012],"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":[0.00007793928,0.00007957288,0.0008959834,0.006369736,0.0002497786,0.0002863377,0.0004438435,0.01209401,0.002282225,0.03946741,0.02425088,0.9135023],"study_design_scores_gemma":[0.00006574962,0.0003284952,0.00339074,0.004920884,0.000745619,0.002813275,0.0007432882,0.1839544,0.008365861,0.1476182,0.6467159,0.0003374906],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.002225243,0.3619235,0.6223994,0.002723897,0.001196312,0.0001398226,0.0003327449,0.00109334,0.007965564],"genre_scores_gemma":[0.054959,0.5068038,0.4206019,0.002299956,0.004654499,0.0004676383,0.001488492,0.0006095345,0.008115122],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.003852273,"threshold_uncertainty_score":0.01404184,"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."}}