Although behavioral studies have documented numerical reasoning errors in large language models (LLMs), the underlying representational mechanisms remain unclear. We hypothesize that numerical attributes occupy shared latent subspaces and investigate two questions:(1) How do LLMs internally integrate multiple numerical attributes of a single entity? (2)How does irrelevant numerical context perturb these representations and their downstream outputs? To address these questions, we combine linear probing with partial correlation analysis and prompt-based vulnerability tests across models of varying sizes. Our results show that LLMs encode real-world numerical correlations but tend to systematically amplify them. Moreover, irrelevant context induces consistent shifts in magnitude representations, with downstream effects that vary by model size. These findings reveal a vulnerability in LLM decision-making and lay the groundwork for fairer, representation-aware control under multi-attribute entanglement.
On the Step Length Confounding in LLM Reasoning Data Selection
College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；Key Laboratory of Symbolic Computation and Knowledge Engineering, MoE, Jilin University（吉林大学符号计算与知识工程教育部重点实验室）；Alibaba Cloud Computing（阿里云）；School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Department of Mathematics, University of Michigan（密歇根大学数学系）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能研究中心）
Interpreting Social Bias in LVLMs via Information Flow Analysis and Multi-Round Dialogue Evaluation
The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；Shandong University（山东大学）；Institute of Deep Perception Technology, JITRI（深度感知技术研究所）
Matched sample selection with GANs for mitigating attribute confounding
University of California at Berkeley（加州大学伯克利分校）；Massachusetts Institute of Technology（麻省理工学院）；California Institute of Technology（加州理工学院）；Amazon Web Services（亚马逊网络服务）
A Confounding Factors-Inhibition Adversarial Learning Framework for Multi-site fMRI Mental Disorder Identification
School of Software, Taiyuan University of Technology（太原科技大学软件学院）；School of Computer Science (Data Science), Taiyuan University of Technology（太原科技大学计算机科学（数据科学）学院）；Max Planck Institute for Human Cognitive and Brain Sciences（马克斯·普朗克人类认知与脑科学研究所）；Department of Psychiatry & Behavioral Sciences, Stanford University（斯坦福大学精神病学与行为科学系）；Montreal Neurological Institute, McGill University（蒙特利尔神经科学研究所，麦吉尔大学）
Interpreting Emergent Extreme Events in Multi-Agent Systems
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；Fu Dan University（福鼎大学）；Tongji University（同济大学）；Renmin University of China（中国人民大学）
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；IIIS, Tsinghua University（清华大学交叉信息研究院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；Deepmind（深度思考）；MIT BCS（麻省理工学院脑与认知科学系）；CBMM（脑、心智与机器中心）
