List your company

Commonsense Question Answering on RiddleSense

67.3AccuracySCORE (GPT-4 Verifier)
56.69259.44662.264.954Apr 26, 2024

Evaluation results

MethodLinks
SCORE (GPT-4 Verifier)Base LM=LLaMA-2-13B-chat, Verifier=gpt-4, Refiner=SCORE (fine-tuned)2024.0467.387.7
SCORE (GPT-4 Verifier)Base LM=Gemma-7B-it, Verifier=gpt-4, Refiner=SCORE (fine-tuned)2024.0464.985.6
Few-shot promptingBase LM=LLaMA-2-13B-chat2024.0457.6—
Few-shot promptingBase LM=Gemma-7B-it2024.0457.1—