Xun Xian

Ice Cream Doesn’t Cause Drowning: Benchmarking LLMs Against Statistical Pitfalls in Causal Inference

STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents

On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains

Understanding Data Poisoning Attacks for RAG: Insights and Algorithms

On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains