collaborators

9 papers

cs.CL2026

Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning

Shanyong Wang, Shuhang Lin, Yining Zhao +2

Recent advances in large language models (LLMs) have significantly improved the alignment of models with general human preferences. However, a major challenge remains in adapting L…

cs.IR2026

RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG Routing

Ziqi Wang, Xi Zhu, Shuhang Lin +3

Retrieval-augmented generation (RAG) has evolved into a family of paradigms with distinct performance profiles and resource demands, turning paradigm selection into a multi-criteri…

cs.CL2025

CTkvr: KV Cache Retrieval for Long-Context LLMs via Centroid then Token Indexing

Kuan Lu, Shuhang Lin, Sai Wu +7

Large language models (LLMs) are increasingly applied in long-context scenarios such as multi-turn conversations. However, long contexts pose significant challenges for inference e…

cs.CL2025

Cache Mechanism for Agent RAG Systems

Shuhang Lin, Zhencan Peng, Lingyao Li +3

Recent advances in Large Language Model (LLM)-based agents have been propelled by Retrieval-Augmented Generation (RAG), which grants the models access to vast external knowledge ba…

cs.AI2025

Know the Ropes: A Heuristic Strategy for LLM-based Multi-Agent System Design

Zhenkun Li, Lingyao Li, Shuhang Lin +1

Single-agent LLMs hit hard limits--finite context, role overload, and brittle domain transfer. Conventional multi-agent fixes soften those edges yet expose fresh pains: ill-posed d…

cs.CR2025

Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models

Junjie Xiong, Changjia Zhu, Shuhang Lin +4

Large Language Models (LLMs) are increasingly equipped with capabilities of real-time web search and integrated with protocols like Model Context Protocol (MCP). This extension cou…