2025
M2S: Multi-turn to Single-turn jailbreak in Red Teaming for LLMs
ACL 2025long
We introduce a novel framework for consolidating multi-turn adversarial “jailbreak” prompts into single-turn queries, significantly reducing the manual overhead required for adversarial testing of large language models (LLMs). While multi-turn human jailbreaks have been shown to yield high attack su…