List your company

Toxicity Evaluation on BOLD

0Toxic RateBase model
-0.6523.7498.1512.551Jul 20, 2025Aug 18, 2025Sep 17, 2025Oct 17, 2025Nov 15, 2025Dec 15, 2025Jan 14, 2026

Evaluation results

MethodLinks
Base modelBackbone=Qwen3-4B, Temperature=0.1, Trials=32026.0100.0310.0243.35——
RADBackbone=Qwen3-4B, Temperature=0.1, Trials=3, β=102026.0100.030.0243.33——
RADBackbone=Qwen3-4B, Temperature=0.1, Trials=3, β=502026.0100.0260.0213.39——
RADBackbone=Qwen3-4B, Temperature=0.1, Trials=3, β=752026.0100.0250.023.5——
RADBackbone=Qwen3-4B, Temperature=0.1, Trials=3, β=1002026.0100.0240.023.64——
RADBackbone=Qwen3-4B, Temperature=0.1, Trials=3, β=3002026.0100.0220.0186.24——
RADBackbone=Qwen3-4B, Temperature=0.1, Trials=3, β=5002026.0100.0230.0211.58——
SASABackbone=Qwen3-4B, Temperature=0.1, Trials=3, β=102026.0100.030.0243.36——
SASABackbone=Qwen3-4B, Temperature=0.1, Trials=3, β=502026.0100.0310.0253.37——
SASABackbone=Qwen3-4B, Temperature=0.1, Trials=3, β=752026.0100.0320.0253.37——
SASABackbone=Qwen3-4B, Temperature=0.1, Trials=3, β=1002026.0100.0320.0253.37——
SASABackbone=Qwen3-4B, Temperature=0.1, Trials=3, β=3002026.0100.0320.0253.82——
SASABackbone=Qwen3-4B, Temperature=0.1, Trials=3, β=5002026.0100.0330.0264.93——
TIDEBackbone=Qwen3-4B, Temperature=0.1, Trials=32026.0100.0250.0213.351—
Universal Self-consistencyGroup=Baselines, Base Model=GPT-3.5-Turbo2025.070—————
MADGroup=Baselines, Base Model=GPT-3.5-Turbo2025.070—————
MEPGroup=Baselines, Base Model=GPT-3.5-Turbo2025.070—————
MetaCrit w/o ϕ↑Group=Ablation, Base Model=GPT-3.5-Turbo2025.070—————
MetaCrit w/o ϕ↓Group=Ablation, Base Model=GPT-3.5-Turbo2025.070—————
MetaCrit + GPT-3.5-TurboGroup=Ours, Base Model=GPT-3.5-Turbo2025.070—————
MetaCrit + DeepSeek-v3Group=Ours, Base Model=DeepSeek-v32025.070—————
MetaCrit + Claude-3.5-SonnetGroup=Ours, Base Model=Claude-3.5-Sonnet2025.070—————
MetaCrit + GPT-4oGroup=Ours, Base Model=GPT-4o2025.070—————
Self-refineGroup=Baselines, Base Model=GPT-3.5-Turbo2025.076.4—————
ExpertPromptingGroup=Baselines, Base Model=GPT-3.5-Turbo2025.0712.9—————
Zero-shot-CoTGroup=Baselines, Base Model=GPT-3.5-Turbo2025.0716.3—————
COFTBackbone=LLaMA-2-13B2026.05——0.079——1
COFTBackbone=Mistral-7B-Instruct2026.05——0.076——1
DExpertsBackbone=LLaMA-2-13B2026.05——0.099——3.3
DExpertsBackbone=Mistral-7B-Instruct2026.05——0.096——3.1
DT-CD⋆Backbone=LLaMA-2-13B2026.05——0.094——2.8
DT-CD⋆Backbone=Mistral-7B-Instruct2026.05——0.092——2.6
SDDBackbone=LLaMA-2-13B2026.05——0.105——4
SDDBackbone=Mistral-7B-Instruct2026.05——0.101——3.9
VanillaBackbone=LLaMA-2-13B2026.05——0.123——5.8
VanillaBackbone=Mistral-7B-Instruct2026.05——0.117——5.8