{"id":"W7125907148","doi":"10.1109/ase63991.2025.00380","title":"TrustVis: A Multi-Dimensional Trustworthiness Evaluation Framework for Large Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; University of Alberta","funders":"","keywords":"Trustworthiness; Robustness (evolution); Voting; Natural language; Key (lock); User interface; Personalization; Feature (linguistics)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004659314,0.0006341711,0.0007166975,0.0003831944,0.00102689,0.0004977353,0.001633072,0.0006499437,0.0006402037],"category_scores_gemma":[0.003039218,0.0006246357,0.0004125887,0.001642029,0.00008801591,0.001388654,0.001250792,0.001042679,0.00004259953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003548758,"about_ca_system_score_gemma":0.001196139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009782014,"about_ca_topic_score_gemma":0.00006278291,"domain_scores_codex":[0.9943454,0.0007148171,0.0009892543,0.001620839,0.001213153,0.001116499],"domain_scores_gemma":[0.9953566,0.001559451,0.0004169681,0.001457463,0.001015752,0.0001937352],"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":[0.00009638751,0.00028962,0.0001363833,0.0001029287,0.0001248743,0.000005305208,0.002402155,0.4510779,0.00001664514,0.4868433,0.0003992037,0.05850529],"study_design_scores_gemma":[0.003914484,0.00006548673,0.0003379177,0.0004324504,0.0002453961,0.000003230326,0.0005390494,0.8907427,0.00008647871,0.1027493,0.0003268991,0.0005565671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003471639,0.002253151,0.9823146,0.002670402,0.004939945,0.002427649,0.00003162316,0.0003384202,0.001552502],"genre_scores_gemma":[0.5156391,0.000009301194,0.4794032,0.001510456,0.0002831102,0.0002226194,0.00003333583,0.00003454538,0.002864246],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5121675,"threshold_uncertainty_score":0.9996205,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03575871934778612,"score_gpt":0.3657391003013337,"score_spread":0.3299803809535476,"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."}}