4 papers
The Trust Paradox in LLM-Based Multi-Agent Systems: When Collaboration Becomes a Security Vulnerability
Zijie Xu, Minfeng Qi, Shiqing Wu +4
Multi-agent systems powered by large language models are advancing rapidly, yet the tension between mutual trust and security remains underexplored. We introduce and empirically va…
Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring
Honglin Mu, Han He, Yuxin Zhou +9
Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential…
Faithful, Unfaithful or Ambiguous? Multi-Agent Debate with Initial Stance for Summary Evaluation
Mahnaz Koupaee, Jake W. Vincent, Saab Mansour +9
Faithfulness evaluators based on large language models (LLMs) are often fooled by the fluency of the text and struggle with identifying errors in the summaries. We propose an appro…
CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation
Han He, Qianchu Liu, Lei Xu +4
Existing automatic prompt engineering methods are typically designed for discriminative tasks, where new task prompts are iteratively refined with limited feedback from a single me…