{"id":"W7062167294","doi":"","title":"Towards Trustworthy AI: Investigating Bias and Confidence Alignment in Large Language Models","year":2024,"lang":"en","type":"other","venue":"Brock University Digital Repository (Brock University)","topic":"Magnetic confinement fusion research","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Trustworthiness; Preference; Inclusion (mineral); Narrative; Security token; Suite; Preference elicitation","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02657039,0.000869073,0.0008681936,0.002217268,0.001121186,0.006218089,0.001622763,0.001611414,0.002325786],"category_scores_gemma":[0.1608643,0.0006020697,0.001056293,0.001589047,0.002408802,0.007119632,0.004873195,0.003348507,0.0008840516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001918043,"about_ca_system_score_gemma":0.002122648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004491384,"about_ca_topic_score_gemma":0.005264567,"domain_scores_codex":[0.9804885,0.01355068,0.001059765,0.001970504,0.002534437,0.0003960808],"domain_scores_gemma":[0.813789,0.1621264,0.006121458,0.01177077,0.005049774,0.001142621],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001325613,0.0002818709,0.1095186,0.001126967,0.0007832017,0.0005876324,0.01248714,0.3529838,0.007353129,0.1460109,0.007315,0.3602261],"study_design_scores_gemma":[0.00004291661,0.0001218374,0.004157884,0.0001526255,0.00005913779,0.0001279549,0.0006604048,0.8575,0.003078356,0.1304651,0.003580239,0.00005353482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.267309,0.001116476,0.7171824,0.002961475,0.0001177101,0.0001975767,0.000946524,0.002664319,0.007504442],"genre_scores_gemma":[0.8764524,0.000214389,0.1202388,0.0003596552,0.00008845183,0.0001555506,0.001265018,0.0004265188,0.0007990489],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9734296,"threshold_uncertainty_score":0.1405194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01445174385072913,"score_gpt":0.2180889780310023,"score_spread":0.2036372341802732,"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."}}