{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005412067,0.0001427762,0.000148243,0.0001068563,0.0001366754,0.0002610476,0.001056983,0.0000539092,0.00001304914],"category_scores_gemma":[0.00001563982,0.0001173896,0.0000276557,0.0003850773,0.00001302156,0.0007763395,0.0007940186,0.0001282955,0.0000931848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004416557,"about_ca_system_score_gemma":0.00006747049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003214361,"about_ca_topic_score_gemma":0.000343627,"domain_scores_codex":[0.9986432,0.00004269224,0.000172281,0.0004842581,0.0002532088,0.0004044107],"domain_scores_gemma":[0.9991448,0.00002455314,0.00004127022,0.0006522891,0.00003828643,0.00009879005],"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":[0.00003021512,0.0002332951,0.001940205,0.00005552168,0.00004711364,0.0002865033,0.01542186,0.4008685,0.02387534,0.5391573,0.001176691,0.01690744],"study_design_scores_gemma":[0.0006625634,0.00002558634,0.000306483,0.00002570744,0.000002037351,0.000007816638,0.0002133006,0.995716,0.0008966083,0.001834691,0.0001231753,0.0001860127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1530209,0.00001327279,0.8423741,0.0004681996,0.00008482134,0.0002076048,0.000002909934,0.0005661902,0.003261969],"genre_scores_gemma":[0.6392707,0.000002098803,0.3569143,0.0002381662,0.00001962697,0.00002345669,0.000004970997,0.00001283248,0.003513816],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5948475,"threshold_uncertainty_score":0.4787007,"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."}}