Showing 2025Show all
2 papers · 1 filter
cs.CR2025
Can LLM Infer Risk Information From MCP Server System Logs?
Jiayi Fu, Yuansen Zhang, Yinggui Wang
Large Language Models (LLMs) demonstrate strong capabilities in solving complex tasks when integrated with external tools. The Model Context Protocol (MCP) has become a standard in…
cs.LG2025
Reward Shaping to Mitigate Reward Hacking in RLHF
Jiayi Fu, Xuandong Zhao, Chengyuan Yao +4
Reinforcement learning from human feedback (RLHF) is widely used to align large language models (LLMs) with human preferences. However, RLHF remains vulnerable to \emph{reward hack…