@article{towardsfaithfulnaturallanguage,
  title = {Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models},
  author = {Wei Jie Yeo and Ranjan Satapathy and Erik Cambria},
  year = {2024},
  eprint = {2410.14155},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.14155v2},
}