Adversarial NLI: A New Benchmark for Natural Language Understanding

We introduce a new large-scale NLI benchmark dataset, collected via an iterative, adversarial human-and-model-in-the-loop procedure. We show that training models on this new dataset leads to state-of-the-art performance on a variety of popular NLI benchmarks, while posing a more difficult challenge with its new test set. Our analysis sheds light on the shortcomings of current state-of-theart models, and shows that non-expert annotators are successful at finding their weaknesses. The data collection method can be applied in a never-ending learning scenario, becoming a moving target for NLU, rather than a static benchmark that will quickly saturate.

• DA
  Defense Advanced Research Projects Agency

  Awards: N66001-19-2-4031, N66001-19
• OO
  Office of Naval Research

  Awards: N00014-18-1-2871, N00014