{"id":"W4389518635","doi":"10.18653/v1/2023.findings-emnlp.776","title":"Detrimental Contexts in Open-Domain Question Answering","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology","keywords":"Computer science; Question answering; Leverage (statistics); Pipeline (software); Open domain; Context (archaeology); Artificial intelligence; Information retrieval; Natural language processing; Matching (statistics); Machine learning; Language model","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":[0.0004169153,0.00004653515,0.00006421929,0.0001021537,0.00003175966,0.0001288133,0.0005905039,0.00002108303,0.00001213189],"category_scores_gemma":[0.00001447826,0.00004528079,0.00001085183,0.0003720068,0.000005536263,0.0004537107,0.0005243522,0.00004876506,0.0001278512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004686219,"about_ca_system_score_gemma":0.00002189826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003589684,"about_ca_topic_score_gemma":0.0001873954,"domain_scores_codex":[0.9993812,0.00003228152,0.0001200773,0.0002157878,0.0000976279,0.0001530028],"domain_scores_gemma":[0.9996972,0.00002860741,0.0000151208,0.0002196987,0.000007954455,0.0000314312],"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":[0.000005709639,0.00005335968,0.0160377,0.000009719971,0.000005448233,0.0001171673,0.001709784,0.001965638,0.01202352,0.8109314,0.0008312226,0.1563092],"study_design_scores_gemma":[0.001606553,0.00007041536,0.0392185,0.00008846922,8.471398e-7,0.00001691795,0.0003376062,0.8874597,0.01247801,0.05563416,0.002718728,0.000370061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3838171,0.00001740262,0.6062603,0.0007476556,0.0002421924,0.0001444539,1.685772e-7,0.0002041497,0.008566567],"genre_scores_gemma":[0.9508657,0.000002382435,0.04821049,0.0001707472,0.00001598493,0.000009982926,7.628398e-7,0.000003028087,0.0007209635],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8854941,"threshold_uncertainty_score":0.1846497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03086295426828448,"score_gpt":0.3123762498647927,"score_spread":0.2815132955965082,"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."}}