3 papers
cs.CL2026
Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs
Mingyu Jin, Yutong Yin, Jingcheng Niu +7
In this work, we investigate how Large Language Models (LLMs) adapt their internal representations when encountering inputs of increasing difficulty, quantified as the degree of ou…
cs.AI2025
Hypothesis-Driven Feature Manifold Analysis in LLMs via Supervised Multi-Dimensional Scaling
Federico Tiblias, Irina Bigoulaeva, Jingcheng Niu +2
The linear representation hypothesis states that language models (LMs) encode concepts as directions in their latent space, forming organized, multidimensional manifolds. Prior wor…
cs.CL2025
Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning
Jingcheng Niu, Subhabrata Dutta, Ahmed Elshabrawy +2
Large-scale Transformer language models (LMs) trained solely on next-token prediction with web-scale data can solve a wide range of tasks after seeing just a few examples. The mech…