Investigating the Benefits of Free-Form Rationales

This publication has 29 references indexed in Scilit:

• e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks
  2021
• Aligning Faithful Interpretations with their Social Attribution
  Transactions of the Association for Computational Linguistics, 2021
• On the Dangers of Stochastic Parrots
  2021
• Shortcut learning in deep neural networks
  Nature Machine Intelligence, 2020
• ERASER: A Benchmark to Evaluate Rationalized NLP Models
  2020
• Towards Faithfully Interpretable NLP Systems: How Should We Define and Evaluate Faithfulness?
  2020
• Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations
  IEEE Transactions on Visualization and Computer Graphics, 2019
• Textual Explanations for Self-Driving Vehicles
  2018
• Generating Visual Explanations
  2016
• The Equivalence of Weighted Kappa and the Intraclass Correlation Coefficient as Measures of Reliability
  Educational and Psychological Measurement, 1973