{"id":"W6910560197","doi":"10.48448/3qqj-9850","title":"Improving Zero-shot Reader by Reducing Distractions from Irrelevant Documents in Open-Domain Question Answering","year":2023,"lang":"en","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Question answering; Selection (genetic algorithm); Set (abstract data type); Overconfidence effect; Language model; Transferability","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":[0.005316604,0.001558564,0.001321542,0.001006661,0.0006866578,0.00230653,0.002492338,0.002658969,0.004782793],"category_scores_gemma":[0.02701228,0.0005759496,0.0007578604,0.0005133026,0.001137866,0.004653701,0.004361394,0.002382178,0.004640216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005040075,"about_ca_system_score_gemma":0.0008550386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00129136,"about_ca_topic_score_gemma":0.002347432,"domain_scores_codex":[0.9951114,0.002799518,0.0001539246,0.00113478,0.0005770139,0.0002233594],"domain_scores_gemma":[0.9801242,0.01485821,0.0006313012,0.002465341,0.001345303,0.0005755981],"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":[0.002369252,0.001584215,0.00668655,0.0008842173,0.0002874148,0.0008245172,0.004999395,0.0127101,0.07732826,0.005433312,0.01539996,0.8714928],"study_design_scores_gemma":[0.0003952552,0.00377879,0.008080349,0.0002143012,0.000468359,0.002648202,0.003385235,0.7628484,0.1491297,0.0419465,0.02677947,0.0003254941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2747918,0.002052124,0.6892362,0.0007381466,0.0002803179,0.0002900196,0.0003471735,0.02474451,0.007519845],"genre_scores_gemma":[0.7708955,0.0003234689,0.2125006,0.001224637,0.0002063133,0.0001962483,0.001312066,0.0009377583,0.01240334],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005316604,"threshold_uncertainty_score":0.02811718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04088398060828208,"score_gpt":0.3519989213068937,"score_spread":0.3111149406986116,"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."}}