Benchmark
CommonsenseQA
A commonsense question-answering benchmark dataset used to evaluate the commonsense reasoning capabilities of models. It consists of multiple-choice questions that require commonsense knowledge to answer correctly.
Timeline (last 90 days)
Sep 18
VisKG-LM achieves improvements of 1.2, 0.8, and 4.3 points over the GreaseLM baseline on the three benchmarks CommonsenseQA, OpenBookQA, and MedQA-USMLE, respectively.
Unverified50%