{"id":"W4416036796","doi":"10.18653/v1/2025.emnlp-main.556","title":"NileChat: Towards Linguistically Diverse and Culturally Aware LLMs for Local Communities","year":2025,"lang":"","type":"article","venue":"","topic":"ICT in Developing Communities","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Ethnic group; Indigenous; Action (physics); Cultural diversity; Work (physics); Qualitative research","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002203421,0.000477643,0.0003361838,0.000635343,0.002110421,0.003599214,0.001825848,0.001360047,0.02824364],"category_scores_gemma":[0.005315895,0.0002594722,0.0003197488,0.0005669867,0.0008568979,0.003860614,0.009718141,0.001658657,0.01023186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001210776,"about_ca_system_score_gemma":0.003233139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007408448,"about_ca_topic_score_gemma":0.01400822,"domain_scores_codex":[0.9987741,0.0005958906,0.00004761874,0.000124753,0.000262101,0.0001955486],"domain_scores_gemma":[0.9973944,0.0005164428,0.0001045525,0.0003658002,0.00068735,0.0009314623],"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":[0.001466282,0.001360648,0.01402855,0.00217483,0.00008852197,0.002322669,0.04620164,0.002219468,0.05864396,0.04781014,0.2043497,0.6193336],"study_design_scores_gemma":[0.0002354834,0.0004007706,0.00824526,0.0006865181,0.00006853964,0.0009062657,0.03833978,0.007109236,0.01730008,0.02178205,0.9047856,0.0001402779],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.2384246,0.002140647,0.2753586,0.01653904,0.001583803,0.002316112,0.008191389,0.05224819,0.4031976],"genre_scores_gemma":[0.5614246,0.0009022586,0.2608766,0.003935829,0.0001232002,0.001948776,0.01251248,0.004068188,0.1542082],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02824364,"threshold_uncertainty_score":0.09448433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03490264759068291,"score_gpt":0.2994294263540569,"score_spread":0.264526778763374,"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."}}