List your company

Question Answering on TriviaQA (F1, SBERT, Acc)

75.3F1 ScoreCRITIC-R1
6.97224.71142.4560.189May 28, 2026

Evaluation results

MethodLinks
CRITIC-R1Method Category=Reflective / Critique Methods2026.0575.38576.3
Search-R1Method Category=Reasoning and Retrieval Baselines, Status=criticized base RAG model2026.0574.984.875
Self-RefineMethod Category=Reflective / Critique Methods2026.0574.344.154.2
Align-RAGMethod Category=Reflective / Critique Methods2026.0571.142.741.2
CoTMethod Category=Reasoning and Retrieval Baselines2026.051646.170.9
Naive-RAGMethod Category=Reasoning and Retrieval Baselines2026.0512.944.774.1
Self-RAGMethod Category=Reflective / Critique Methods2026.0510.141.268
VanillaMethod Category=Base LLM Generation2026.059.635.445.2