Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts

Mikayel Samvelyan, Sharath Raparthy, Andrei Lupu, Eric Hambro, Aram Markosyan, manish bhatt, Yuning Mao, Minqi Jiang, Jack Parker-Holder, Jakob Foerster, Tim Rocktäschel, Roberta Raileanu

Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts: 16 upvotes on Hugging Face Daily Papers, #10 of 10 papers on 2024-02-27. Day-by-day upvote history.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.