3 papers
cs.LG2026
Step-Level Sparse Autoencoder for Reasoning Process Interpretation
Xuan Yang, Jiayu Liu, Yuhang Lai +3
Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated…
cs.LG2026
NodeSynth: Socially Aligned Synthetic Data for AI Evaluation
Qazi Mamunur Rashid, Xuan Yang, Zhengzhe Yang +5
Recent advancements in generative AI facilitate large-scale synthetic data generation for model evaluation. However, without targeted approaches, these datasets often lack the soci…
q-bio.NC2026
Multifaceted neural representation of words in naturalistic language
Xuan Yang, Chuanji Gao, Cheng Xiao +2
Understanding how the brain represents the multifaceted properties of words in context is essential for explaining the neural architecture of human language. Here, we combine large…