{"id":"W4412448221","doi":"10.1007/s44196-026-01341-9","title":"Infusing Syntax and Semantics into LLMs","year":2025,"lang":"en","type":"preprint","venue":"International Journal of Computational Intelligence Systems","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Ministério da Ciência, Tecnologia e Inovação; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo; International Business Machines Corporation","keywords":"Syntax; Semantics (computer science); Linguistics; Computer science; Programming language; Natural language processing; Philosophy","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001228349,0.0003207114,0.0005239192,0.000998577,0.00007068264,0.001232438,0.002957468,0.000259943,0.000002281681],"category_scores_gemma":[0.0005202975,0.0002950167,0.0001631102,0.0002726572,0.000114852,0.0006793714,0.001866793,0.0009038647,0.000004010416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004367633,"about_ca_system_score_gemma":0.00118248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001575082,"about_ca_topic_score_gemma":0.000005036978,"domain_scores_codex":[0.9962823,0.0001779634,0.001351299,0.0003991365,0.001607149,0.0001821432],"domain_scores_gemma":[0.9925513,0.0004938671,0.001507069,0.0002748803,0.005030558,0.0001422734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005611375,0.0001340992,0.0003193939,0.0005333309,0.0007134315,0.0004439451,0.003575975,0.5453319,0.00006880279,0.339918,0.001974286,0.1069308],"study_design_scores_gemma":[0.0001062399,0.00006275556,0.00002760017,0.002724445,0.00003051299,0.0008592141,0.0001557731,0.3847601,0.0006930811,0.6091933,0.001075119,0.0003119302],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00143827,0.01200674,0.9776809,0.002075349,0.006202897,0.0001929558,0.0000164914,0.0001100874,0.0002763667],"genre_scores_gemma":[0.5843579,0.0001698418,0.4147519,0.0001823147,0.0004326061,0.00000558785,0.00001234486,0.000009922875,0.00007754062],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5829197,"threshold_uncertainty_score":0.9999502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01979539401522895,"score_gpt":0.33857610026688,"score_spread":0.3187807062516511,"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."}}