Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts

Mikayel Samvelyan, Sharath Chandra Raparthy,Andrei Lupu,Eric Hambro, Aram H. Markosyan, Manish Bhatt, Yuning Mao,Minqi Jiang, Jack Parker-Holder,Jakob Foerster,Tim Rocktäschel,Roberta Raileanu

CoRR(2024)

引用 0|浏览11
暂无评分
摘要
As large language models (LLMs) become increasingly prevalent across many real-world applications, understanding and enhancing their robustness to user inputs is of paramount importance. Existing methods for identifying adversarial prompts tend to focus on specific domains, lack diversity, or require extensive human annotations. To address these limitations, we present Rainbow Teaming, a novel approach for producing a diverse collection of adversarial prompts. Rainbow Teaming casts adversarial prompt generation as a quality-diversity problem, and uses open-ended search to generate prompts that are both effective and diverse. It can uncover a model's vulnerabilities across a broad range of domains including, in this paper, safety, question answering, and cybersecurity. We also demonstrate that fine-tuning on synthetic data generated by Rainbow Teaming improves the safety of state-of-the-art LLMs without hurting their general capabilities and helpfulness, paving the path to open-ended self-improvement.
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要