Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts

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.

Using Captum to Explain Generative Language Models

Captum is a comprehensive library for model explainability in PyTorch, offering a range of methods from the interpretability literature to enhance users' understanding of PyTorch models. In this paper, we introduce new features in Captum that are specifically designed to analyze the behavior of generative language models. We provide an overview of the available functionalities and example applications of their potential for understanding learned associations within generative language models.

Identifying and Disentangling Spurious Features in Pretrained Image Representations

Neural networks employ spurious correlations in their predictions, resulting in decreased performance when these correlations do not hold. Recent works suggest fixing pretrained representations and training a classification head that does not use spurious features. We investigate how spurious features are represented in pretrained representations and explore strategies for removing information about spurious features. Considering the Waterbirds dataset and a few pretrained representations, we find that even with full knowledge of spurious features, their removal is not straightforward due to entangled representation. To address this, we propose a linear autoencoder training method to separate the representation into core, spurious, and other features. We propose two effective spurious feature removal approaches that are applied to the encoding and significantly improve classification performance measured by worst group accuracy.

Tell Your Story: Task-Oriented Dialogs for Interactive Content Creation

People capture photos and videos to relive and share memories of personal significance. Recently, media montages (stories) have become a popular mode of sharing these memories due to their intuitive and powerful storytelling capabilities. However, creating such montages usually involves a lot of manual searches, clicks, and selections that are time-consuming and cumbersome, adversely affecting user experiences. To alleviate this, we propose task-oriented dialogs for montage creation as a novel interactive tool to seamlessly search, compile, and edit montages from a media collection. To the best of our knowledge, our work is the first to leverage multi-turn conversations for such a challenging application, extending the previous literature studying simple media retrieval tasks. We collect a new dataset C3 (Conversational Content Creation), comprising 10k dialogs conditioned on media montages simulated from a large media collection. We take a simulate-and-paraphrase approach to collect these dialogs to be both cost and time efficient, while drawing from natural language distribution. Our analysis and benchmarking of state-of-the-art language models showcase the multimodal challenges present in the dataset. Lastly, we present a real-world mobile demo application that shows the feasibility of the proposed work in real-world applications. Our code and data will be made publicly available.

Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models

Despite their wide adoption, the underlying training and memorization dynamics of very large language models is not well understood. We empirically study exact memorization in causal and masked language modeling, across model sizes and throughout the training process. We measure the effects of dataset size, learning rate, and model size on memorization, finding that larger language models memorize training data faster across all settings. Surprisingly, we show that larger models can memorize a larger portion of the data before over-fitting and tend to forget less throughout the training process. We also analyze the memorization dynamics of different parts of speech and find that models memorize nouns and numbers first; we hypothesize and provide empirical evidence that nouns and numbers act as a unique identifier for memorizing individual training examples. Together, these findings present another piece of the broader puzzle of trying to understand what actually improves as models get bigger.