2 papers
cs.AI2025
REMA: A Unified Reasoning Manifold Framework for Interpreting Large Language Model
Bo Li, Guanzhi Deng, Ronghao Chen +5
Understanding how Large Language Models (LLMs) perform complex reasoning and their failure mechanisms is a challenge in interpretability research. To provide a measurable geometric…
cs.CL2024
ROME: Memorization Insights from Text, Logits and Representation
Bo Li, Qinghua Zhao, Lijie Wen
Previous works have evaluated memorization by comparing model outputs with training corpora, examining how factors such as data duplication, model size, and prompt length influence…