AutoRed: A Free-form Adversarial Prompt Generation Framework for Automated Red Teaming
This addresses LLM safety evaluation for AI developers, offering a more effective red teaming method, though it appears incremental as it builds on existing red teaming concepts.
The paper tackles the problem of limited semantic diversity in adversarial prompt generation for LLM safety by proposing AutoRed, a free-form framework that removes the need for seed instructions, achieving higher attack success rates and better generalization than existing baselines.
The safety of Large Language Models (LLMs) is crucial for the development of trustworthy AI applications. Existing red teaming methods often rely on seed instructions, which limits the semantic diversity of the synthesized adversarial prompts. We propose AutoRed, a free-form adversarial prompt generation framework that removes the need for seed instructions. AutoRed operates in two stages: (1) persona-guided adversarial instruction generation, and (2) a reflection loop to iteratively refine low-quality prompts. To improve efficiency, we introduce a verifier to assess prompt harmfulness without querying the target models. Using AutoRed, we build two red teaming datasets -- AutoRed-Medium and AutoRed-Hard -- and evaluate eight state-of-the-art LLMs. AutoRed achieves higher attack success rates and better generalization than existing baselines. Our results highlight the limitations of seed-based approaches and demonstrate the potential of free-form red teaming for LLM safety evaluation. We will open source our datasets in the near future.