{"id":"W4415428125","doi":"10.3233/faia251331","title":"ALF: A Fine-Grained French Analogical Dataset for Evaluating Lexical Knowledge of Large Language Models","year":2025,"lang":"","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Fluency; Lexical item; Lexicographical order; Key (lock); Vocabulary; Computational linguistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00122298,0.0005026366,0.0008429417,0.0006321123,0.0003680007,0.0001708016,0.001516251,0.0005528206,0.00003671811],"category_scores_gemma":[0.0002564444,0.0005000306,0.0001988681,0.0005937049,0.0004982951,0.000316362,0.0006988359,0.000674015,0.00000562784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009366569,"about_ca_system_score_gemma":0.0003083074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007891278,"about_ca_topic_score_gemma":0.000206644,"domain_scores_codex":[0.9964149,0.00007997314,0.001390849,0.001273329,0.000293904,0.0005470738],"domain_scores_gemma":[0.9975631,0.0004472082,0.0004913819,0.0009648799,0.0003892798,0.000144169],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002568318,0.0001823465,0.000004104541,0.0001989615,0.00003182235,0.000001608752,0.0007417861,0.00006477984,0.0001633023,0.5919675,0.001929025,0.4046891],"study_design_scores_gemma":[0.0000542445,0.0001222748,7.154608e-7,0.0003387987,0.0000723448,0.000001799359,0.0002026392,0.3944353,0.002201067,0.5976945,0.004536454,0.0003399275],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001614683,0.01572698,0.9763395,0.0004349413,0.0001972557,0.002029245,0.003736882,0.00007846326,0.001440641],"genre_scores_gemma":[0.06507605,0.0006160095,0.9276305,0.0002615041,0.0002846595,0.001142307,0.002531434,0.00004106765,0.002416394],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4043491,"threshold_uncertainty_score":0.9997451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07860967414722973,"score_gpt":0.3867682798869631,"score_spread":0.3081586057397334,"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."}}