{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004371388,0.0007855099,0.0012792,0.0009869726,0.0004842039,0.002243858,0.001119835,0.001134525,0.005111641],"category_scores_gemma":[0.02679398,0.0008325086,0.0006764934,0.001984358,0.000976442,0.005551112,0.001537313,0.003082388,0.001971455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008553402,"about_ca_system_score_gemma":0.0006677528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001363681,"about_ca_topic_score_gemma":0.00237266,"domain_scores_codex":[0.9983739,0.0009914857,0.00007252242,0.0002470487,0.000251,0.00006408778],"domain_scores_gemma":[0.9773319,0.02046373,0.0003653668,0.001024871,0.000670058,0.0001440503],"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":[0.0002725871,0.0001082422,0.003688968,0.0007704298,0.0002982696,0.0002919272,0.0005458983,0.08802928,0.004814658,0.4682567,0.03848936,0.3944336],"study_design_scores_gemma":[0.00001839852,0.00003202909,0.0007088361,0.00006816621,0.00006253017,0.0001366774,0.00004457006,0.4200761,0.00160227,0.5698555,0.007369566,0.00002534628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02413854,0.008436072,0.9515447,0.003057497,0.0006693206,0.0000320907,0.000581069,0.001523625,0.01001697],"genre_scores_gemma":[0.6497983,0.01312988,0.2804224,0.001789051,0.003540379,0.0003215454,0.003316512,0.002529071,0.04515281],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005111641,"threshold_uncertainty_score":0.02311838,"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."}}