{"id":"W4409740531","doi":"10.1007/s10994-025-06767-4","title":"Developing safe and responsible large language model: can we balance bias reduction and language understanding?","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Vector Institute","funders":"","keywords":"Reduction (mathematics); Balance (ability); Computer science; Cognitive psychology; Linguistics; Psychology; Mathematics; 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":[0.0005942171,0.0001582774,0.0001728757,0.0002823299,0.0003507011,0.0002435602,0.0002405359,0.00008066875,0.000002869463],"category_scores_gemma":[0.0002842525,0.0001465052,0.00001978038,0.0004867848,0.00004097721,0.0002831168,0.0004085837,0.0003836839,6.447812e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000130196,"about_ca_system_score_gemma":0.0001061829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001480105,"about_ca_topic_score_gemma":0.0001048335,"domain_scores_codex":[0.9988884,0.0001308366,0.0001614267,0.0004009127,0.0001437608,0.0002746712],"domain_scores_gemma":[0.9995331,0.0001103199,0.00008593172,0.0001971319,0.00002577984,0.00004774494],"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":[0.0001059856,0.00003822781,0.01477652,0.0006009443,0.00006750139,0.0001373827,0.03667421,0.0003987018,0.03507942,0.7956886,0.0003654642,0.1160671],"study_design_scores_gemma":[0.0009806409,0.00007545627,0.0003637202,0.001000986,0.0000262302,0.0001102083,0.003181064,0.8893731,0.01874628,0.08475613,0.0007597822,0.0006264533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07788008,0.01300966,0.9022833,0.005409324,0.00006936101,0.0001246768,0.000003257413,0.0006882701,0.0005320699],"genre_scores_gemma":[0.7921398,0.0001404715,0.2058877,0.0002716343,0.00001810602,0.000005459434,0.000006088601,0.00001148046,0.001519299],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8889744,"threshold_uncertainty_score":0.5974307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02426265180724371,"score_gpt":0.3020835596657921,"score_spread":0.2778209078585484,"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."}}