Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations
Published in The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026, CCF-A), 2026
Recommended citation: W. Luo, G. Peng, Wei Li, S. Wei, F. Song, L. Wang, N. Yang, X. Zhang, J. Jin, et al. (2026). "Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations." The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026, CCF-A).
Download Paper