Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals

no code implementations • 16 Nov 2023 • Yanai Elazar, Bhargavi Paranjape, Hao Peng, Sarah Wiegreffe, Khyathi Raghavi, Vivek Srikumar, Sameer Singh, Noah A. Smith

Previous work has found that datasets with paired inputs are prone to correlations between a specific part of the input (e. g., the hypothesis in NLI) and the label; consequently, models trained only on those outperform chance.

counterfactual In-Context Learning +2