{"id":"W4410041812","doi":"10.1007/978-3-031-87499-4_11","title":"Evaluating Large Language Models on Cybersecurity Knowledge and Skills: A Comparative Analysis","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Information and Cyber Security","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Computer science; Computer security; Natural language processing; Software engineering; Artificial intelligence","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":[0.001552243,0.0004950174,0.0007339346,0.001633811,0.0004030355,0.0005469599,0.001780398,0.0002599174,0.00002245951],"category_scores_gemma":[0.00006794398,0.000448362,0.0001926091,0.001544779,0.0003080201,0.0008412507,0.001387634,0.0008265249,0.0000292409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002539652,"about_ca_system_score_gemma":0.000463134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002863068,"about_ca_topic_score_gemma":0.000447263,"domain_scores_codex":[0.996757,0.00009508103,0.0005543865,0.001202085,0.000832024,0.0005594207],"domain_scores_gemma":[0.9974493,0.0006135002,0.0002894102,0.001146823,0.0003409615,0.0001599591],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001039037,0.0001529168,0.00003278927,0.0000795432,0.0001621596,0.00002537015,0.06300195,0.04895706,0.000006006267,0.5624573,0.00007559288,0.3250389],"study_design_scores_gemma":[0.0003378446,0.0001012739,0.0001151964,0.0002084021,0.0000510163,0.000005214577,0.000003267361,0.9499279,0.0001509047,0.04827066,0.0003792045,0.0004491358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007089943,0.0006819811,0.9494877,0.0001683259,0.0004812989,0.0003743465,0.00002527204,0.0001365713,0.04793547],"genre_scores_gemma":[0.8494554,0.0000464956,0.1470309,0.002377241,0.0001453653,0.0000174324,0.00002850241,0.00001147545,0.0008871708],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9009708,"threshold_uncertainty_score":0.9997968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02611560327253232,"score_gpt":0.3291824211190175,"score_spread":0.3030668178464851,"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."}}