TruthfulQA

Dataset Card for TruthfulQA Dataset Summary TruthfulQA: Measuring How Models Mimic Human Falsehoods We propose a benchmark to measure whether a language model is truthful in generating answers to questions. The benchmark comprises 817 questions that span 38 categories, including health, law, finance and politics. We cr

Papers using TruthfulQA (4)

RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation2025 · 2 citesPost-Training is About States, Not Tokens: A State Distribution View of SFT, RL, and On-Policy Distillation2026LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction2025RLHF Workflow: From Reward Modeling to Online RLHF2024 · 3 cites