List your company

Commonsense Reasoning on Date (test)

73.5AccuracyFaithful CoT + Voting
69.828870.781971.73572.6881Jun 6, 2023

Evaluation results

MethodLinks
Faithful CoT + VotingLLM=GPT-3.5-turbo, Prompting Format=Faithful CoT, Voting Strategy=Majority Voting, k=102023.0673.5
Ours (Natural Program (NP), No Verification)LLM=GPT-3.5-turbo, Prompting Format=Natural Program (NP), Verification Method=None, Voting Strategy=Majority Voting, k=102023.0672.49
Ours (NP + Deductive Verification + UPV)LLM=GPT-3.5-turbo, Prompting Format=Natural Program (NP), Verification Method=Deductive Verification, Voting Strategy=UPV, k=102023.0671.45
CoT + VotingLLM=GPT-3.5-turbo, Prompting Format=Chain-of-Thought (CoT), Voting Strategy=Majority Voting, k=102023.0669.97