Skip to content

Interpretability

Jump to bottom
crazyofapple edited this page Jul 25, 2022 · 6 revisions

Free-text Explanations

  1. Reframing Human-AI Collaboration for Generating Free-Text Explanations, NAACL 2022

  2. Can language models learn from explanations in context?, DeepMind, 2022

  3. The Unreliability of Explanations in Few-Shot In-Context Learning, Greg Durrett Group, 2022

  4. E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning, ACL findings, 2022

Explanation Quality

  1. On the Sensitivity and Stability of Model Interpretations in NLP, ACL, 2022

  2. Logic Traps in Evaluating Attribution Scores , ACL, 2022

  3. Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training, ARR, 2022

Clone this wiki locally