On the Universal Truthfulness Hyperplane Inside LLMs

On the Universal Truthfulness Hyperplane Inside LLMs Junteng Liu author Shiqi Chen author Yu Cheng author Junxian He author 2024-11 text Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication liu-etal-2024-universal 10.18653/v1/2024.emnlp-main.1012 https://aclanthology.org/2024.emnlp-main.1012/ 2024-11 18199 18224