{"id":"W4413065313","doi":"10.1007/978-981-96-6294-4_20","title":"Word Embedding Bias in Large Language Models","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Word (group theory); Word embedding; Computer science; Natural language processing; Embedding; Linguistics; Artificial intelligence; 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":[],"consensus_categories":[],"category_scores_codex":[0.001510065,0.000183253,0.0002394156,0.001563898,0.0002529519,0.0005309138,0.003659294,0.0001192995,0.000004048716],"category_scores_gemma":[0.00005071145,0.0001930694,0.00003724145,0.0005832104,0.0002037413,0.007007624,0.003769796,0.0004987004,0.0000169573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001785867,"about_ca_system_score_gemma":0.0003197782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002868238,"about_ca_topic_score_gemma":0.00005016911,"domain_scores_codex":[0.998346,0.00003359534,0.0006916829,0.0002992518,0.0003579338,0.0002714798],"domain_scores_gemma":[0.9970648,0.0002127435,0.0002089996,0.002284819,0.0001656336,0.00006297153],"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":[4.807723e-7,0.000007750841,0.00002479954,0.00001871537,0.000001405196,5.288092e-7,0.004012238,0.003744945,3.550023e-7,0.7850717,0.00005610385,0.207061],"study_design_scores_gemma":[0.0002008143,0.000006100621,0.0001114042,0.000319138,0.000001311068,0.000004332381,0.00004747814,0.9689337,0.000001834226,0.01606278,0.01412865,0.0001824532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009455665,0.0004598268,0.7634304,0.0005500591,0.00018947,0.0002276986,0.000006378019,0.00007176496,0.2349699],"genre_scores_gemma":[0.2618826,0.003051334,0.725899,0.003088013,0.00005051066,0.00005635113,0.00005976254,0.00001316941,0.005899203],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9651887,"threshold_uncertainty_score":0.7873142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0730375053919994,"score_gpt":0.3315808165141487,"score_spread":0.2585433111221493,"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."}}