{"id":"W4416037105","doi":"10.18653/v1/2025.emnlp-main.69","title":"LingGym: How Far Are LLMs from Thinking Like Field Linguists?","year":2025,"lang":"","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Field (mathematics); Perspective (graphical)","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":[0.01228182,0.00121849,0.0007871602,0.002003147,0.001221065,0.005404155,0.002997685,0.002617029,0.01109636],"category_scores_gemma":[0.04917743,0.0005825032,0.0007744517,0.001568125,0.002689213,0.01712847,0.004476529,0.003631948,0.005843833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001765403,"about_ca_system_score_gemma":0.00316964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006071735,"about_ca_topic_score_gemma":0.007496345,"domain_scores_codex":[0.9942672,0.00306851,0.0002660372,0.00109237,0.001006422,0.0002995385],"domain_scores_gemma":[0.968793,0.0174971,0.001001241,0.00898417,0.002082883,0.001641609],"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":[0.002090286,0.0007897054,0.06142915,0.00186838,0.0004017982,0.0003657692,0.008511277,0.02384347,0.009955204,0.06709547,0.09501864,0.7286309],"study_design_scores_gemma":[0.0005260214,0.001308297,0.02991814,0.001224992,0.0002167107,0.000816959,0.01022808,0.2554868,0.02518361,0.4233727,0.2514397,0.000278027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5439097,0.006225882,0.2501646,0.01977324,0.0008925192,0.0005607234,0.01021793,0.05997256,0.108283],"genre_scores_gemma":[0.8230624,0.00112507,0.1477199,0.003026315,0.0001594218,0.0003055913,0.01316787,0.003067827,0.008365612],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01228182,"threshold_uncertainty_score":0.06495327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01102998744758834,"score_gpt":0.2717450584029037,"score_spread":0.2607150709553154,"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."}}