一作ACL 2026Findings· Findings of ACL
How Do LLM s "Trust" Unknown Knowledge? An Unknown Knowledge Based Jailbreak Attack
Yixiao Huang · Lan Zhang · Chaoran Wang
摘要
Learning unknown knowledge through ICL and RAG can enhance LLM capabilities in specialized fields. While most research focuses on how to identify and utilize such knowledge, little work examines what factors lead LLMs to trust and adopt it, leaving models prone to errors and harmful content. Grou...