List your company

Veracity Inference on COMMONSENSEQA 1,000 examples

0.935Mean Hamming SimilarityVeracity Search (VS)
0.485720.602360.7190.83564May 17, 2025

Evaluation results

MethodLinks
Veracity Search (VS)Base LM=Qwen-4B2025.050.935
Veracity Search (VS)Base LM=Qwen-8B2025.050.931
Veracity Search (VS)Base LM=Llama-8B2025.050.903
Veracity Search (VS)Base LM=Llama-3B2025.050.836
CoTBase LM=Qwen-4B2025.050.695
RecursiveBase LM=Qwen-4B2025.050.607
CoTBase LM=Qwen-8B2025.050.59
CoTBase LM=Llama-8B2025.050.535
Many2ManyBase LM=Qwen-8B2025.050.534
VotingBase LM=Qwen-8B2025.050.533
VotingBase LM=Qwen-4B2025.050.521
Many2ManyBase LM=Qwen-4B2025.050.517
RecursiveBase LM=Qwen-8B2025.050.509
CoTBase LM=Llama-3B2025.050.507
RecursiveBase LM=Llama-8B2025.050.506
RecursiveBase LM=Llama-3B2025.050.505
VotingBase LM=Llama-8B2025.050.505
Many2ManyBase LM=Llama-3B2025.050.504
VotingBase LM=Llama-3B2025.050.504
Many2ManyBase LM=Llama-8B2025.050.503