Co-occurring keywords · papers mentioning both
Papers
Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps
EMNLP 2025
Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models
EMNLP 2025
On Measuring Faithfulness or Self-consistency of Natural Language Explanations
ACL 2024
Measuring and Improving Faithfulness of Attention in Neural Machine Translation
EACL 2021