A `state of the art' model A surpasses humans in a benchmark B, but fails on similar benchmarks C, D, and E. What does B have that the other benchmarks do not? Recent research provides the answer: spurious bias. However, developing A to solve benchmarks B through E does not guarantee that it will solve future benchmarks. To progress towards a model that `truly learns' an underlying task, we need to quantify the differences between successive benchmarks, as opposed to existing binary and black-box approaches. We propose a novel approach to solve this underexplored task of quantifying benchmark quality by debuting a data quality metric: DQI.
@article{arxiv.2008.03964,
title = {DQI: A Guide to Benchmark Evaluation},
author = {Swaroop Mishra and Anjana Arunkumar and Bhavdeep Sachdeva and Chris Bryan and Chitta Baral},
journal= {arXiv preprint arXiv:2008.03964},
year = {2020}
}