{"id":"W4393924586","doi":"10.48550/arxiv.2404.01399","title":"Developing Safe and Responsible Large Language Model : Can We Balance Bias Reduction and Language Understanding in Large Language Models?","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Government of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Business","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005762363,0.002060932,0.001323625,0.0009661885,0.0006837121,0.002581367,0.0033866,0.00207331,0.003588965],"category_scores_gemma":[0.03281884,0.0008852244,0.001569347,0.0009315038,0.001515875,0.007233524,0.00304242,0.004954404,0.004936168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001420308,"about_ca_system_score_gemma":0.003221633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006896275,"about_ca_topic_score_gemma":0.01608587,"domain_scores_codex":[0.9972044,0.001433384,0.0001559074,0.0007378263,0.0002979445,0.0001705268],"domain_scores_gemma":[0.9901623,0.005683968,0.0003594424,0.002605394,0.0009095644,0.0002793359],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009631324,0.0005018561,0.01346417,0.001102094,0.0005207114,0.0004767639,0.001411578,0.2724908,0.02500492,0.02505021,0.04128578,0.617728],"study_design_scores_gemma":[0.0001786942,0.0001509881,0.000737806,0.0001023311,0.0001057139,0.0001355024,0.0002259167,0.9215601,0.01531124,0.05060309,0.01082108,0.0000675484],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07686141,0.00207396,0.8780382,0.003045175,0.0003124571,0.0003216277,0.003067206,0.03219871,0.004081323],"genre_scores_gemma":[0.4420123,0.0008770543,0.5315648,0.002678346,0.0001883677,0.0009735117,0.01278157,0.004156093,0.004767777],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006896275,"threshold_uncertainty_score":0.03047466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1296299817314392,"score_gpt":0.2345049574943663,"score_spread":0.1048749757629271,"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."}}