Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Embracing Anisotropy: Turning Massive Activations into Interpretable Control Knobs for Large Language Models
Youngji Roh, Hyunjin Cho, Jaehyung Kim
Large Language Models (LLMs) exhibit highly anisotropic internal representations, often characterized by massive activations, a phenomenon where a small subset of feature dimension…
cs.CL2025
Revisiting the UID Hypothesis in LLM Reasoning Traces
Minju Gwak, Guijin Son, Jaehyung Kim
Large language models (LLMs) often solve problems using step-by-step Chain-of-Thought (CoT) reasoning, yet these intermediate steps are frequently unfaithful or hard to interpret.…