{"id":"W4414209357","doi":"10.1177/02655322251348685","title":"Advancing language assessment for teaching and learning in the era of the artificial intelligence (AI) revolution: Promises and challenges","year":2025,"lang":"en","type":"article","venue":"Language Testing","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Japan Society for the Promotion of Science; Waseda University","keywords":"Language assessment; Language proficiency; Language acquisition; Applications of artificial intelligence; Assessment for learning; Teaching method","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":[],"consensus_categories":[],"category_scores_codex":[0.001757634,0.0001118067,0.0001548855,0.0000586237,0.0007475544,0.0001159314,0.0001396504,0.00002938337,0.00001663336],"category_scores_gemma":[0.002600129,0.00007082817,0.00003228499,0.00005018956,0.0001259148,0.0001122084,0.00007478649,0.0008792472,1.660746e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001988695,"about_ca_system_score_gemma":0.0000312204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001429765,"about_ca_topic_score_gemma":0.002114912,"domain_scores_codex":[0.9989185,0.0003702898,0.0002306891,0.0001923736,0.00009647573,0.0001916847],"domain_scores_gemma":[0.9978697,0.001828024,0.0001155477,0.0001441543,0.0000288906,0.0000136808],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.000005948374,0.00002595493,0.001391932,0.0002963231,0.00001176557,0.00000435305,0.3203359,0.00009481444,0.0007880256,0.05944712,0.000008399749,0.6175895],"study_design_scores_gemma":[0.0002025884,0.000115103,0.005608365,0.001309743,0.00005652868,0.00001632228,0.9757233,0.01262298,0.000211843,0.001914747,0.002014853,0.0002036162],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9741301,0.01030394,0.0006319328,0.002710881,0.0001117608,0.000340868,0.000003098197,0.00006943182,0.011698],"genre_scores_gemma":[0.9961234,0.00001565312,0.002917601,0.0003752391,0.000198031,0.00003035032,0.000002378198,0.00001039782,0.0003269205],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6553874,"threshold_uncertainty_score":0.574966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0365263602611972,"score_gpt":0.3059178929668351,"score_spread":0.2693915327056379,"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."}}