{"id":"W4389520156","doi":"10.18653/v1/2023.findings-emnlp.85","title":"MoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Model","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Canadian Institute for Advanced Research; Nvidia","keywords":"Computer science; Baseline (sea); Modality (human–computer interaction); Ranking (information retrieval); Task (project management); Modalities; Artificial intelligence; Codebase; Modal; Benchmark (surveying); Shot (pellet); Language model; Information retrieval; Domain (mathematical analysis); Machine learning; Natural language processing; Programming language; Source code; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.00320702,0.002858087,0.001635383,0.002149075,0.001159123,0.002879811,0.005445841,0.004234976,0.02241825],"category_scores_gemma":[0.01489705,0.0009538771,0.002918331,0.001577766,0.001243332,0.006410411,0.007039716,0.004931134,0.01263631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001811697,"about_ca_system_score_gemma":0.002688788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01146872,"about_ca_topic_score_gemma":0.0223069,"domain_scores_codex":[0.9969845,0.001027239,0.0001728915,0.001121794,0.0005163117,0.000177253],"domain_scores_gemma":[0.9961172,0.001995297,0.0001267714,0.001013781,0.0005110857,0.0002357412],"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":[0.0006013827,0.0007109529,0.002214061,0.002392488,0.0005098595,0.0004725561,0.0008841904,0.03345464,0.01553324,0.01949729,0.3548805,0.5688489],"study_design_scores_gemma":[0.000274853,0.0002807919,0.001186033,0.0001518889,0.0001170606,0.0006038816,0.0004679754,0.8187597,0.01239841,0.07656693,0.08906853,0.0001238163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009559362,0.001906872,0.8168662,0.001623712,0.000500313,0.0009401492,0.01460546,0.1481379,0.005860093],"genre_scores_gemma":[0.1354342,0.0006705797,0.7826332,0.002069001,0.0003205954,0.001614336,0.06424981,0.003661601,0.009346569],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02241825,"threshold_uncertainty_score":0.07499653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04094407819874246,"score_gpt":0.3138173639312929,"score_spread":0.2728732857325505,"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."}}