{"id":"W6939706559","doi":"10.60692/y4yp8-ya908","title":"Zero-shot Visual Question Answering with Language Model Feedback","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Mycorrhizal Fungi and Plant Interactions","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Closed captioning; Leverage (statistics); Language model; Context (archaeology); Task (project management); Question answering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002483121,0.002483877,0.001566493,0.001674732,0.0008882399,0.002098737,0.004872184,0.003597205,0.01175299],"category_scores_gemma":[0.01137399,0.0006035682,0.00137262,0.001024198,0.001203039,0.005166704,0.003418416,0.002983358,0.00455869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001701509,"about_ca_system_score_gemma":0.001519017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007242381,"about_ca_topic_score_gemma":0.008136041,"domain_scores_codex":[0.9970281,0.001138691,0.000120448,0.001048671,0.0004861311,0.0001780614],"domain_scores_gemma":[0.9944899,0.003301886,0.0002305216,0.0008491096,0.0009071245,0.0002214302],"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":[0.0007706916,0.0007799715,0.001344136,0.00169428,0.0002010376,0.0004734269,0.001351574,0.05727545,0.04611229,0.01315003,0.06995353,0.8068935],"study_design_scores_gemma":[0.0001403595,0.0004265793,0.000661812,0.0001090726,0.0001078636,0.0003432011,0.0004100617,0.9045308,0.02763313,0.03735717,0.02817143,0.000108483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01594716,0.001995319,0.9362873,0.0008372474,0.0004073275,0.0005352732,0.001876098,0.0366386,0.005475643],"genre_scores_gemma":[0.3464301,0.0006880216,0.6262577,0.002317776,0.0004778655,0.000707727,0.01227624,0.001486246,0.009358414],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01175299,"threshold_uncertainty_score":0.03931767,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02669832996227935,"score_gpt":0.2187333300525713,"score_spread":0.192035000090292,"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."}}