ResearchBenchmarksQuestion Answering on TruthfulQA MC2 0-shot (test)Follow64.27AccuracyTRL58.86260.26661.6763.074Sep 30, 2025Evaluation ResultsMethodMethodLinksAccuracyTRLModel Backbone=Qwen2.5...Model Backbone=Qwen2.5-7B, Evaluation Protocol=0-shot2025.0964.27OPPOModel Backbone=Qwen2.5...Model Backbone=Qwen2.5-7B, Evaluation Protocol=0-shot2025.0964.03OPPOModel Backbone=Qwen2.5...Model Backbone=Qwen2.5-3B, Evaluation Protocol=0-shot2025.0959.99TRLModel Backbone=Qwen2.5...Model Backbone=Qwen2.5-3B, Evaluation Protocol=0-shot2025.0959.07