List your company

Question Answering on AI2SciE Far OOD

96.2AccuracyFew-shot*
67.49674.94882.489.852Sep 26, 2025

Evaluation results

MethodLinks
Few-shot*Model=Llama3.1-70B2025.0996.2
ICRModel=Llama3.1-70B2025.0992
ICRModel=Qwen3-32B2025.0988.6
Zero-shotModel=Qwen3-32B2025.0985.8
I2CLModel=Qwen3-32B2025.0984.6
I2CLModel=Llama3.1-70B2025.0984.4
FVModel=Llama3.1-70B2025.0980.8
Few-shot*Model=Qwen3-32B2025.0980.3
FVModel=Qwen3-32B2025.0979.4
Zero-shotModel=Llama3.1-70B2025.0968.6