4 papers · 1 filter
Latent Trajectory Dynamics in Large Language Models: A Manifold Evolution Framework with Empirical Validation
Yukun Zhang, Qi Dong, Mengkang Li
Understanding how latent representations evolve during generation is a central open problem in large language model interpretability. We introduce \textbf{Dynamical Manifold Evolut…
Emergent Hierarchical Structure in Large Language Models: An Information-Theoretic Framework for Multi-Scale Representation
Yukin Zhang, Qi Dong, Kemu Xu
Why do language models from different architecture families respond so differently to the same perturbation? We argue that the answer is not scale, but \emph{how architecture shape…
Hierarchical Alignment: Surgical Fine-Tuning via Functional Layer Specialization in Large Language Models
Yukun Zhang, Qi Dong
Existing alignment techniques for Large Language Models (LLMs), such as Direct Preference Optimization (DPO), typically treat the model as a monolithic entity, applying uniform opt…
Multi-Scale Manifold Alignment for Interpreting Large Language Models: A Unified Information-Geometric Framework
Yukun Zhang, Qi Dong
We present Multi-Scale Manifold Alignment(MSMA), an information-geometric framework that decomposes LLM representations into local, intermediate, and global manifolds and learns cr…