{"id":"W7082245767","doi":"10.48448/x0gg-7n40","title":"NativQA: Multilingual Culturally-Aligned Natural Query for LLMs","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmarking; Benchmark (surveying); Construct (python library); Scripting language; Question answering; Natural language","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006895991,0.0004007313,0.0003914745,0.0004037622,0.000395997,0.0003188188,0.003955228,0.0002776222,0.00009700371],"category_scores_gemma":[0.001558921,0.0003228456,0.0001322435,0.001022614,0.0006067434,0.0002828728,0.001160928,0.0002538047,0.00003880625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001103819,"about_ca_system_score_gemma":0.001077999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001477473,"about_ca_topic_score_gemma":0.0001312472,"domain_scores_codex":[0.997097,0.00002418483,0.0003466401,0.001231112,0.0005779677,0.0007230527],"domain_scores_gemma":[0.9978511,0.0001883829,0.0002888221,0.001006685,0.0005280534,0.0001369493],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000183424,0.0002597704,0.00004496966,0.0006001705,0.0001363547,0.00005098328,0.0008421451,0.0002234907,0.01535504,0.1336304,0.7478216,0.1010168],"study_design_scores_gemma":[0.0008691208,0.00008904541,0.00002346163,0.0004229791,0.00002832061,0.00002714983,0.0002469641,0.1270889,0.01614882,0.01452558,0.839455,0.001074611],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00006313886,0.00122183,0.1662572,0.00871497,0.005515913,0.001282828,0.00006709548,0.001439481,0.8154376],"genre_scores_gemma":[0.02183031,0.00002396182,0.1197819,0.000798069,0.0004788504,0.00004815276,0.00005566263,0.00002572789,0.8569574],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1268655,"threshold_uncertainty_score":0.9999223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01320524591029865,"score_gpt":0.2839877655436504,"score_spread":0.2707825196333517,"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."}}