Are self-explanations from Large Language Models faithful?

Are self-explanations from Large Language Models faithful? Andreas Madsen author Sarath Chandar author Siva Reddy author 2024-08 text Findings of the Association for Computational Linguistics: ACL 2024 Lun-Wei Ku editor Andre Martins editor Vivek Srikumar editor Association for Computational Linguistics Bangkok, Thailand conference publication madsen-etal-2024-self 10.18653/v1/2024.findings-acl.19 https://aclanthology.org/2024.findings-acl.19/ 2024-08 295 337