{"id":"W4416035278","doi":"10.18653/v1/2025.emnlp-main.1667","title":"From Chat Logs to Collective Insights: Aggregative Question Answering","year":2025,"lang":"","type":"article","venue":"","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Question answering; Questions and answers; The Internet; Conversation analysis","routes":{"ca_aff":true,"ca_fund":true,"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":[0.004440162,0.001700321,0.0008586114,0.005246135,0.001370563,0.00268217,0.001972208,0.002209733,0.002271979],"category_scores_gemma":[0.01951319,0.0004213599,0.001223777,0.00306979,0.0007971575,0.004836639,0.003407953,0.002301848,0.00206187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001119308,"about_ca_system_score_gemma":0.001374327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01139951,"about_ca_topic_score_gemma":0.02403073,"domain_scores_codex":[0.9945478,0.002890597,0.0004085356,0.001164607,0.0007291857,0.0002592559],"domain_scores_gemma":[0.9872645,0.007189491,0.0007310876,0.002675007,0.001441185,0.0006987666],"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":[0.002092115,0.002555624,0.1258931,0.004722507,0.001080303,0.00204573,0.01198622,0.0489778,0.02524731,0.01877025,0.3007807,0.4558484],"study_design_scores_gemma":[0.0002959931,0.0005862039,0.06821366,0.0004808604,0.0002800072,0.001137787,0.00978989,0.6666681,0.01375111,0.06116851,0.1773826,0.0002453275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4436562,0.01023233,0.2034947,0.009062123,0.001235274,0.002150425,0.2856374,0.02660071,0.01793073],"genre_scores_gemma":[0.504218,0.0008092074,0.1939162,0.001085073,0.0004824903,0.001289344,0.2940779,0.0003474402,0.003774358],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01139951,"threshold_uncertainty_score":0.02348208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01396950052420981,"score_gpt":0.2798178028179277,"score_spread":0.2658483022937179,"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."}}