3 papers
cs.CL2026
RCCM: Diagnosing Gains and Harms in Reasoning-Prompt Transfer
Yuqi Zhang, Di Zhang
A reasoning prompt can improve one deployment and degrade another. RCCM (Reasoning-Control Capability Mismatch) examines these reversals by pairing answers to the same questions wi…
cs.CL2026
The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content
Yuqi Zhang, Di Zhang
Retrieval-augmented generation (RAG) systems inject external knowledge to improve LLM outputs, yet the format of injected content -- distinct from its semantic relevance -- can ind…
cs.LG2025
Data-Efficient Machine Learning Potentials via Difference Vectors Based on Local Atomic Environments
Xuqiang Shao, Yuqi Zhang, Di Zhang +10
Constructing efficient and diverse datasets is essential for the development of accurate machine learning potentials (MLPs) in atomistic simulations. However, existing approaches o…