{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02427495,0.001836413,0.001962887,0.004278426,0.001467758,0.005117739,0.002454897,0.002939873,0.003853571],"category_scores_gemma":[0.1213195,0.001087476,0.002550377,0.002774871,0.001410975,0.01219423,0.007423452,0.003295417,0.003603055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001492785,"about_ca_system_score_gemma":0.002275521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002487863,"about_ca_topic_score_gemma":0.002503648,"domain_scores_codex":[0.9743555,0.01184393,0.002395326,0.005023122,0.00571627,0.0006658542],"domain_scores_gemma":[0.9038031,0.07347433,0.003394164,0.01165101,0.006773194,0.0009043141],"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":[0.001871771,0.001165909,0.06365358,0.003233564,0.001296347,0.0009202071,0.006686562,0.07276873,0.052373,0.04571025,0.03314719,0.717173],"study_design_scores_gemma":[0.000291581,0.0008430468,0.01538729,0.0004712388,0.001101343,0.001363051,0.001623377,0.7201125,0.04780333,0.136522,0.07416985,0.0003112831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2210912,0.008967307,0.7131218,0.007550837,0.0006747764,0.0005272183,0.002760542,0.02738517,0.01792114],"genre_scores_gemma":[0.7176386,0.001421936,0.2697199,0.001331541,0.0004035131,0.0001530315,0.006385291,0.001068392,0.001877783],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02427495,"threshold_uncertainty_score":0.1283797,"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."}}