collaborators

5 papers

cs.CR2026

Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework

Zhaoqi Wang, Daqing He, Zijian Zhang +13

While retrieval-augmented generation systems partially address the hallucination issues in large language models, it also introduces new vulnerabilities to knowledge corruption att…

cs.SE2026

On the Effectiveness of Context Compression for Repository-Level Tasks: An Empirical Investigation

Jia Feng, Zhanyue Qin, Cuiyun Gao +4

Repository-level code intelligence tasks require large language models (LLMs) to process long, multi-file contexts. Such inputs introduce three challenges: crucial context can be o…

cs.CL2025

Quantifying Conversation Drift in MCP via Latent Polytope

Haoran Shi, Hongwei Yao, Shuo Shao +4

The Model Context Protocol (MCP) enhances large language models (LLMs) by integrating external tools, enabling dynamic aggregation of real-time data to improve task execution. Howe…

cs.LG2025

BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF

Kaiwen Duan, Hongwei Yao, Yufei Chen +4

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning text-to-image (T2I) models with human preferences. However, RLHF's feedback mechanism also opens new pathw…

cs.CR2025

ControlNET: A Firewall for RAG-based LLM System

Hongwei Yao, Haoran Shi, Yidou Chen +3

Retrieval-Augmented Generation (RAG) has significantly enhanced the factual accuracy and domain adaptability of Large Language Models (LLMs). This advancement has enabled their wid…