Trustworthy AI: Ensuring Reliability and Accountability from Models to Agents

Abstract

In this thesis, we develop algorithms with theoretical guarantees for ensuring reliability and accountability of Machine Learning (ML) systems. As ML systems evolve from predictive models to generative models and autonomous agents, the landscape of trustworthy AI shifted. This thesis introduces tools grounded in information theory, optimization, and statistical learning to mitigate bias, reduce arbitrary decisions, ensure content provenance, and evaluate LLM-driven agents in autonomous settings. Towards mitigating bias and arbitrariness in traditional ML models, we introduce a kernel-based method to achieve multiaccuracy across complex subpopulations that tradi- tional demographic categories may overlook. We also develop methods to address predictive multiplicity—where equally accurate models yield conflicting individual predictions. We ensure the accountability in generative AI through watermarking large language models (LLMs). We characterize the information-theoretic trade-off between watermark detection and text distortion and deriving optimal watermarking strategies by leveraging optimal transport and coding theory. Empirical evaluations show our watermarks achieve a superior detection-quality tradeoff across language generation and coding tasks. Finally, we evaluate autonomous LLM agents in multi-agent environments through the first simulator of a fully LLM-driven supply chain. While agents can outperform human experts, reducing costs by up to 67%, we identify systemic risks such as costly tail events.