{"id":"W4404783635","doi":"10.18653/v1/2024.findings-emnlp.83","title":"EchoSight: Advancing Visual-Language Models with Wiki Knowledge","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Visual language; Human–computer interaction; Natural language processing; Knowledge management; World Wide Web; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001652995,0.0001392726,0.0001054347,0.0001401703,0.0001035985,0.0002654608,0.0004852651,0.00003626169,0.0000468956],"category_scores_gemma":[0.000007283115,0.0001009062,0.0000374573,0.0006390956,0.00002285694,0.0006252,0.0001763065,0.0002207807,0.0005166443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005475761,"about_ca_system_score_gemma":0.00008889793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000219442,"about_ca_topic_score_gemma":0.00008732895,"domain_scores_codex":[0.9989414,0.00003373676,0.0001304066,0.0004810278,0.00015601,0.0002574676],"domain_scores_gemma":[0.9992567,0.0001304488,0.00002031751,0.0004491301,0.00003916728,0.0001042493],"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":[0.000002512709,0.00009664215,0.0001550986,0.00006634113,0.00002953824,0.00003125648,0.005913731,0.01949325,0.002892741,0.6725904,0.0008402157,0.2978882],"study_design_scores_gemma":[0.00007938632,0.00005956205,0.0002711281,0.00004915444,0.000005144066,0.00001909935,0.00003238876,0.9935144,0.0009905667,0.002234844,0.002579946,0.0001644165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02662303,0.0005416931,0.93758,0.0007760252,0.00009908757,0.0001573289,5.862536e-7,0.001416144,0.03280604],"genre_scores_gemma":[0.7959023,0.000004187353,0.2022136,0.0001133647,0.00008105393,0.0000470937,0.00000189726,0.00001802008,0.001618593],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9740211,"threshold_uncertainty_score":0.6640589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007573520661421284,"score_gpt":0.3036279570150422,"score_spread":0.2960544363536209,"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."}}