11 papers
RLPF: Reinforcement Learning from Performance Feedback for Code Generation
Huihao Jing, Haozhe Cui, Wenbin Hu +9
The paper introduces RLPF, a reinforcement‑learning approach that uses staged performance feedback to train code‑generation models to produce not only correct programs but also fas…
Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions
Huihao Jing, Wenbin Hu, Shaojin Chen +10
The paper surveys how isolating components such as user inputs, tools, execution, inter‑agent communication, and environment can improve safety of LLM‑agent systems, presenting a b…
OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset
Wenbin Hu, Huihao Jing, Haochen Shi +3
Ensuring the safety and compliance of large language models (LLMs) is of paramount importance. However, existing LLM safety datasets often rely on ad-hoc taxonomies for data genera…
ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance
Haoran Li, Yulin Chen, Huihao Jing +6
Individuals' concerns about data privacy and AI safety are highly contextualized and extend beyond sensitive patterns. Addressing these issues requires reasoning about the context…
GrandGuard: Taxonomy, Benchmark, and Safeguards for Elderly-Chatbot Interaction Safety
Changxuan Fan, Xi Yang, Yueyuan Zheng +9
As older adults increasingly use LLM-based chatbots for companionship and assistance, a safety gap is emerging. Older adults may face vulnerabilities from social isolation, limited…
MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning
Huihao Jing, Wenbin Hu, Hongyu Luo +4
Multi-agent systems (MAS), leveraging the remarkable capabilities of Large Language Models (LLMs), show great potential in addressing complex tasks. In this context, integrating MA…