Large Language Models (LLMs) often encode whether a statement is true as a vector in their residual stream activations. These vectors, also known as truth vectors, have been studied in prior work, however how they change when context is introduced remains unexplored. We study this question by measuring (1) the directional change ($θ$) between the truth vectors with and without context and (2) the relative magnitude of the truth vectors upon adding context. Across four LLMs and four datasets, we find that (1) truth vectors are roughly orthogonal in early layers, converge in middle layers, and may stabilize or continue increasing in later layers; (2) adding context generally increases the truth vector magnitude, i.e., the separation between true and false representations in the activation space is amplified; (3) larger models distinguish relevant from irrelevant context mainly through directional change ($θ$), while smaller models show this distinction through magnitude differences. We also find that context conflicting with parametric knowledge produces larger geometric changes than parametrically aligned context. Collectively, these findings provide a geometric characterization of how context transforms the truth vector in the activation space of LLMs.
Encyclo-K: Evaluating LLMs with Dynamically Composed Knowledge Statements
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Nanjing University（南京大学）；The University of Manchester（曼彻斯特大学）
Can large language models generate salient negative statements?
Peoples' Friendship University of Russia (RUDN University)（俄罗斯人民友谊大学（RUDN大学））；Joint Institute for Nuclear Research（联合核研究所）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；University of Skövde（舍夫德大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Bosch Center for AI（博世人工智能中心）
Ground Truth Generation for Multilingual Historical NLP using LLMs
ARTFL Project, Romance Languages and Literatures, University of Chicago（ARTFL项目， Romance语言与文学系，芝加哥大学）；Department of History, University of Chicago（历史系，芝加哥大学）；Libraries and School of Information Studies, Purdue University（图书馆与信息科学学院，普渡大学）
Large Language Models are biased to overestimate profoundness
Pontificia Universidad Católica de Chile（智利天主教大学）；Centro Nacional de Inteligencia Artificial (CENIA)（国家人工智能中心）；Brown University（布朗大学）；Leiden University（莱顿大学）
TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Key Laboratory of AI Safety, Chinese Academy of Sciences（中国科学院人工智能安全重点实验室）
Truth Knows No Language: Evaluating Truthfulness Beyond English
HiTZ Center - Ixa, University of the Basque Country, UPV/EHU（希茨中心-ixa，巴斯克大学，UPV/EHU）；Elhuyar（埃尔胡亚尔）；Centro de Investigación en Tecnoloxías Intelixentes (CiTIUS), Universidade de Santiago de Compostela（智能技术研究中心（CiTIUS），圣地亚哥-德孔波斯特拉大学）；Departament de Traducció i Ciències del Llenguatge, Universitat Pompeu Fabra（翻译与语言科学部门，庞培法布拉大学）
How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence
University of California, Los Angeles（加州大学洛杉矶分校）；University of Alberta（阿尔伯塔大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Harvard University（哈佛大学）
Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts
Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS)（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Key Laboratory of AI Safety, Chinese Academy of Sciences（中国科学院人工智能安全重点实验室）
In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search
University of Southern California（南加州大学）；Ohio State University（俄亥俄州立大学）；Fudan University（复旦大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of Pittsburgh（匹兹堡大学）；University of Washington（华盛顿大学）；Cornell University（康奈尔大学）
