List your company

Commonsense Question Answering on QASC

72.8AccuracySCORE (GPT-4 Verifier)
64.68866.79468.971.006Apr 26, 2024

Evaluation results

MethodLinks
SCORE (GPT-4 Verifier)Base LM=Gemma-7B-it, Verifier=gpt-4, Refiner=SCORE (fine-tuned)2024.0472.889.9
SCORE (GPT-4 Verifier)Base LM=LLaMA-2-13B-chat, Verifier=gpt-4, Refiner=SCORE (fine-tuned)2024.0468.185.9
Few-shot promptingBase LM=LLaMA-2-13B-chat2024.0465.9—
Few-shot promptingBase LM=Gemma-7B-it2024.0465—