{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007317334,0.0003609739,0.0003880033,0.0006802608,0.0001657429,0.0002335488,0.0005856573,0.0003016671,0.000004627564],"category_scores_gemma":[0.00004197374,0.0004209581,0.00007378354,0.0006334201,0.00005433895,0.0004294152,0.002677317,0.0008331992,0.000004787831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006676874,"about_ca_system_score_gemma":0.0004139706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005085103,"about_ca_topic_score_gemma":0.001328718,"domain_scores_codex":[0.9974923,0.0001691384,0.0002697452,0.001364709,0.0001393368,0.0005648427],"domain_scores_gemma":[0.9988524,0.00009312292,0.000141568,0.0007327033,0.00003496365,0.0001452172],"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":[0.00004878933,0.00003934114,0.0006510683,0.0005443088,0.00006136418,0.001087797,0.03933522,0.1523965,0.0003736824,0.8047707,0.00002851935,0.000662725],"study_design_scores_gemma":[0.0005429782,0.000009989088,0.00004143418,0.000622481,0.00002939782,0.0000175732,0.009570642,0.8784612,0.0001156384,0.1101729,0.000005026516,0.0004108135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4995723,0.001293607,0.4976563,0.0003844774,0.0001600374,0.0001923388,0.00003864484,0.0001652045,0.0005370064],"genre_scores_gemma":[0.9886359,0.0006534814,0.009086405,0.00008191849,0.00005610344,0.000002104473,0.00001768608,0.00003287888,0.001433515],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7260647,"threshold_uncertainty_score":0.9998242,"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."}}