{"id":"W4411119714","doi":"10.18653/v1/2025.naacl-long.613","title":"JAWAHER: A Multidialectal Dataset of Arabic Proverbs for LLM Benchmarking","year":2025,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"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":"Benchmarking; Arabic; Computer science; Natural language processing; Artificial intelligence; Information retrieval; Linguistics; Philosophy","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":[0.001375926,0.002025889,0.00104725,0.007188035,0.001894778,0.001968449,0.002600086,0.002690795,0.01897864],"category_scores_gemma":[0.007294597,0.0005108528,0.001020583,0.003645954,0.0007322779,0.003242156,0.003781938,0.001735724,0.02754272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001221107,"about_ca_system_score_gemma":0.001576675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009783871,"about_ca_topic_score_gemma":0.01702728,"domain_scores_codex":[0.9984096,0.0003950059,0.0002163337,0.000314045,0.0005160581,0.0001489068],"domain_scores_gemma":[0.9965437,0.0009126667,0.000220133,0.0009041064,0.001048475,0.000370933],"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":[0.001109733,0.0006542907,0.006523114,0.002855561,0.0001997332,0.001073814,0.0009381283,0.002186571,0.01294447,0.004243645,0.8510517,0.1162192],"study_design_scores_gemma":[0.0008103573,0.0002864527,0.02867329,0.0005712769,0.0001515451,0.001584827,0.002210645,0.02503155,0.01882145,0.004360701,0.9172658,0.0002320991],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0691063,0.005649462,0.01259037,0.001878979,0.00126003,0.0009396833,0.8337311,0.04127471,0.03356937],"genre_scores_gemma":[0.04258007,0.000504218,0.01831669,0.0003453661,0.0001269426,0.0005928377,0.9303032,0.00106069,0.006169927],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01897864,"threshold_uncertainty_score":0.06348991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008947348003498994,"score_gpt":0.2973077930139572,"score_spread":0.2883604450104582,"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."}}