[2601.07422] Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations

Computer Science > Computation and Language arXiv:2601.07422 (cs) [Submitted on 12 Jan 2026 (v1), last revised 15 Apr 2026 (this version, v2)] Title:Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations Authors:Wen Luo, Guangyue Peng, Wei Li, Shaohang Wei, Feifan Song, Liang Wang, Nan Yang, Xingxing Zhang, Jing Jin, Furu Wei, Houfeng Wang View a PDF of the paper titled Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations, by Wen Luo and 10 other authors View PDF HTML (experimental) Abstract:Despite their impressive capabilities, large language models (LLMs) frequently generate hallucinations. Previous work shows that their internal states encode rich signals of truthfulness, yet the origins and mechanisms of these signals remain unclear. In this paper, we demonstrate that truthfulness cues arise from two distinct information pathways: (1) a Question-Anchored pathway that depends on question-answer information flow, and (2) an Answer-Anchored pathway that derives self-contained evidence from the generated answer itself. First, we validate and disentangle these pathways through attention knockout and token patching. Afterwards, we uncover notable and intriguing properties of these two mechanisms. Further experiments reveal that (1) the two mechanisms are closely associated with LLM knowledge boundaries; and (2) internal representations are aware of their distinctions. Finally, building on these insightful findings, two applica...