{"id":"W4385571970","doi":"10.18653/v1/2023.acl-short.72","title":"Using contradictions improves question answering systems","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Contradiction; Question answering; Computer science; Context (archaeology); Inference; Logical consequence; Natural language processing; Natural language; Artificial intelligence; Epistemology; Philosophy","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":[0.0001993466,0.0000482762,0.0000602847,0.00008799359,0.0001017744,0.0001415389,0.000186431,0.00002624116,9.738916e-7],"category_scores_gemma":[0.00001461331,0.00004520113,0.00001918596,0.0002716033,0.000006808593,0.0003372414,0.00006537389,0.0000438964,0.00003028795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003431228,"about_ca_system_score_gemma":0.00002377802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003981254,"about_ca_topic_score_gemma":0.000004771488,"domain_scores_codex":[0.9994323,0.00002158046,0.0001194064,0.0001721869,0.0001027658,0.0001517268],"domain_scores_gemma":[0.9996483,0.00002605357,0.00002306908,0.0002369808,0.00002700848,0.00003859578],"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":[5.683675e-7,0.000009918955,0.0005504212,0.00002901574,0.00001550966,0.00001326388,0.0004780372,0.1181761,0.08088738,0.7824302,0.0001735981,0.01723604],"study_design_scores_gemma":[0.00005006865,0.000005475629,0.0004340158,0.00001302417,0.000001512373,0.0000103787,0.00004661997,0.997987,0.0003671401,0.0006425831,0.0003864185,0.00005577489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05968169,0.00003789618,0.9368232,0.0001801274,0.001040721,0.00007904807,3.11796e-7,0.0008317621,0.001325245],"genre_scores_gemma":[0.9697945,0.000004745527,0.02952944,0.00003077347,0.0001034751,0.000006337568,5.619327e-7,0.000004322369,0.000525915],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9101127,"threshold_uncertainty_score":0.1843249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06175751992041341,"score_gpt":0.296440335908989,"score_spread":0.2346828159885757,"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."}}