{"id":"W7106836210","doi":"10.48448/xnwh-ed82","title":"Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Survey","year":2025,"lang":"","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":"Ambiguity; Question answering; Context (archaeology); Relevance (law); Natural language; Categorization; Flexibility (engineering); Ambiguity resolution","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":[0.008254444,0.001060446,0.001538288,0.009809316,0.001928283,0.006239074,0.002692295,0.003111106,0.005097951],"category_scores_gemma":[0.01930399,0.001103879,0.001223264,0.01017193,0.003735782,0.01422942,0.005002666,0.002576439,0.003180661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001964257,"about_ca_system_score_gemma":0.00305692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003808298,"about_ca_topic_score_gemma":0.002532982,"domain_scores_codex":[0.9924078,0.003209577,0.0008554268,0.001583624,0.001649028,0.0002944411],"domain_scores_gemma":[0.9830059,0.01297304,0.0007253177,0.001369595,0.001647499,0.000278571],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009480666,0.00010228,0.002692244,0.005350555,0.00008639014,0.0001657656,0.003115812,0.002822425,0.001473747,0.08181284,0.01203906,0.8902442],"study_design_scores_gemma":[0.00002052427,0.0001130231,0.003226382,0.003524993,0.0001459718,0.001483645,0.003466275,0.01968233,0.003137772,0.17401,0.7910327,0.0001562251],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.009517229,0.7744892,0.1812159,0.007974288,0.0009091333,0.0001908419,0.0003596488,0.001159355,0.0241844],"genre_scores_gemma":[0.1695367,0.4995711,0.3071895,0.006613543,0.004539043,0.000448675,0.002069724,0.0007479375,0.009283774],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.009809316,"threshold_uncertainty_score":0.04365414,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06164557016331745,"score_gpt":0.3568258230869692,"score_spread":0.2951802529236517,"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."}}