{"id":"W4411780569","doi":"10.5539/elt.v18n7p48","title":"Evaluating GPT-4 Turbo`s Ability to Design English Reading Test Items for Language Learners","year":2025,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Reading (process); Test (biology); Linguistics; Language assessment; Mathematics education","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.01243861,0.0006909062,0.0005223717,0.001090758,0.0002352576,0.001458242,0.0009567236,0.0006054415,0.002877658],"category_scores_gemma":[0.06921574,0.0003390032,0.0005481416,0.0005090606,0.0006134,0.001506205,0.002503399,0.0007223633,0.001772485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004760498,"about_ca_system_score_gemma":0.001168648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006618724,"about_ca_topic_score_gemma":0.001165002,"domain_scores_codex":[0.9939054,0.002896081,0.0006126555,0.0007385474,0.001598361,0.0002489515],"domain_scores_gemma":[0.9483709,0.03470654,0.004012987,0.004154401,0.007075148,0.001679996],"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":[0.002110928,0.003007355,0.420244,0.0007393656,0.0001221459,0.0006235864,0.02403267,0.007496672,0.05003619,0.001122081,0.002879952,0.487585],"study_design_scores_gemma":[0.0006600707,0.02785526,0.7170206,0.0004653079,0.0004087012,0.004144287,0.02537716,0.07405181,0.1195974,0.003486621,0.02657533,0.0003572979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.983401,0.00003746681,0.01293442,0.00004498757,0.00001432921,0.0005290935,0.0001476965,0.000493365,0.002397696],"genre_scores_gemma":[0.9495689,0.00009169822,0.0464716,0.00007157188,0.000009169136,0.0005449025,0.0005801384,0.0001071107,0.002555028],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01243861,"threshold_uncertainty_score":0.06578243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02722475778468759,"score_gpt":0.3750710716186919,"score_spread":0.3478463138340043,"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."}}