activity
20242026
collaborators

11 papers

cs.CL2026

Beyond Static Alignment: Hierarchical Policy Control for LLM Safety via Risk-Aware Chain-of-Thought

Jianfeng Si, Lin Sun, Weihong Lin +1

Large Language Models (LLMs) face a fundamental safety-helpfulness trade-off due to static, one-size-fits-all safety policies that lack runtime controllabilityxf, making it difficu…

cs.LG2026

TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment

Zhewen Tan, Wenhan Yu, Jianfeng Si +9

In recent years, safety risks associated with large language models have become increasingly prominent, highlighting the urgent need to mitigate the generation of toxic and harmful…

cs.CV2025

TextlessRAG: End-to-End Visual Document RAG by Speech Without Text

Peijin Xie, Shun Qian, Bingquan Liu +3

Document images encapsulate a wealth of knowledge, while the portability of spoken queries enables broader and flexible application scenarios. Yet, no prior work has explored knowl…

cs.CL2025

Router Upcycling: Leveraging Mixture-of-Routers in Mixture-of-Experts Upcycling

Junfeng Ran, Guangxiang Zhao, Yuhan Wu +7

The Mixture-of-Experts (MoE) models have gained significant attention in deep learning due to their dynamic resource allocation and superior performance across diverse tasks. Howev…

cs.AI2025

Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM

Yongfu Zhu, Lin Sun, Guangxiang Zhao +2

In this work, we introduce Entropy Area Score (EAS), a simple yet effective metric to quantify uncertainty in the answer generation process of reasoning large language models (LLMs…

cs.CL2025

Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training

Jianfeng Si, Lin Sun, Zhewen Tan +1

Current methods for content safety in Large Language Models (LLMs), such as Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), often rely on multi-…