3 papers
cs.IT2026
A Theoretical Interpretation of In-Context Learning via Probabilistic Modeling
Zhenyu Liu, Huaze Tang, Shao-Lun Huang
In-context learning (ICL) is an emerging paradigm that employs the semantic information inherent in large language models (LLMs) for generating answers to user queries. While the r…
cs.IT2025
On Theoretical Interpretations of Concept-Based In-Context Learning
Huaze Tang, Tianren Peng, Shao-lun Huang
In-Context Learning (ICL) has emerged as an important new paradigm in natural language processing and large language model (LLM) applications. However, the theoretical understandin…
cs.CL2025
GRAF: Multi-turn Jailbreaking via Global Refinement and Active Fabrication
Hua Tang, Lingyong Yan, Yukun Zhao +3
Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks. Nevertheless, they still pose notable safety risks due to potential misuse for malicious…