Compound AI systems, comprising multiple interacting components such as LLM agents and external tools, demonstrate state-of-the-art results across diverse tasks. It is hence crucial to align components within the system to produce consistent results that match human expectations. However, conventional alignment methods, such as Direct Preference Optimization (DPO), are not directly applicable to compound AI systems. These challenges include the non-differentiable interactions between components, making end-to-end gradient optimization infeasible. Additionally, system-level preferences cannot be directly translated into component-level preferences, further complicating alignment. We address the issues by formulating compound AI systems as Directed Acyclic Graphs (DAGs), capturing the connections between agents and the data generation processes. We propose a system-level DPO (SysDPO) to jointly align compound systems by adapting the DPO to operate on these DAGs. We study the joint alignment of an LLM and a diffusion model to demonstrate the effectiveness of our approach. Our exploration provides insights into the alignment of compound AI systems and lays a foundation for future advancements.

Federated Domain Adaptation (FDA) describes the federated learning setting where a set of source clients work collaboratively to improve the performance of a target client where limited data is available. The domain shift between the source and target domains, coupled with sparse data in the target domain, makes FDA a challenging problem, e.g., common techniques such as FedAvg and fine-tuning, often fail with the presence of significant domain shift and data scarcity. To comprehensively understand the problem, we introduce metrics that characterize the FDA setting and put forth a theoretical framework for analyzing the performance of aggregation rules. We also propose a novel aggregation rule for FDA, Federated Gradient Projection ($\texttt{FedGP}$), used to aggregate the source gradients and target gradient during training. Importantly, our framework enables the development of an $\textit{auto-weighting scheme}$ that optimally combines the source and target gradients. This scheme improves both $\texttt{FedGP}$ and a simpler heuristic aggregation rule ($\texttt{FedDA}$). Experiments on synthetic and real-world datasets verify the theoretical insights and illustrate the effectiveness of the proposed method in practice.

We study (differentially) private federated learning (FL) of language models. The language models in cross-device FL are relatively small, which can be trained with meaningful formal user-level differential privacy (DP) guarantees when massive parallelism in training is enabled by the participation of a moderate size of users. Recently, public data has been used to improve privacy-utility trade-offs for both large and small language models. In this work, we provide a systematic study of using large-scale public data and LLMs to help differentially private training of on-device FL models, and further improve the privacy-utility tradeoff by techniques of distillation. Moreover, we propose a novel distribution matching algorithm with theoretical grounding to sample public data close to private data distribution, which significantly improves the sample efficiency of (pre-)training on public data. The proposed method is efficient and effective for training private model by taking advantage of public data, especially for customized on-device architectures that do not have ready-to-use pre-trained models.