List your company
ResearchFormerly WizWand

Truthfulness Evaluation on TruthfulQA (TQA Metric)

54.9TQA ScoreEvoPref-Best
50.63651.74352.8553.957May 10, 2026
Updated 5mo ago

Evaluation results

MethodLinks
EvoPref-BestOptimization Paradigm=Multi-Objective Evolutionary, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0554.9
EvoPrefOptimization Paradigm=Multi-Objective Evolutionary, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0553.3
SMS-EMOAOptimization Paradigm=Multi-Objective Evolutionary, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0552.9
MOEA/DOptimization Paradigm=Multi-Objective Evolutionary, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0552.5
IPOOptimization Paradigm=Gradient-Based, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0552
DPOOptimization Paradigm=Gradient-Based, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0551.8
ORPOOptimization Paradigm=Gradient-Based, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0551.5
CMA-ESOptimization Paradigm=Single-Objective Evolutionary, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0551.1
KTOOptimization Paradigm=Gradient-Based, Base Model=Mistral-7B-Instruct-v0.2, LoRA Rank=16, LoRA Alpha=322026.0550.8