Michal Moshkovitz
Michal Moshkovitz is a Researcher at Google Research dedicated to bridging the gap between practical machine learning and rigorous theoretical understanding. Her current research interests span the foundations of Reinforcement Learning (RL) for Large Language Models (LLMs), Explainable AI (XAI), souping strategies, and dynamic RL policies. Michal frequently contributes to the broader ML community through workshop organization and publications at venues like ICML and NeurIPS.
Research Areas
Authored Publications
Sort By
Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods
Suraj Srinivas
Lesia Semenova
Nave Frost
Valentyn Boreiko
Shichang Zhang
Himabindu Lakkaraju
Cynthia Rudin
Jenn Wortman Vaughan
2026
Preview abstract
Despite the proliferation of Explainable AI (XAI) techniques—from feature attributions to sparse autoencoders—explanations rarely influence real-world workflows. In practice, they are often generated and discarded without guiding meaningful action. This gap reflects foundational shortcomings: research has not yet established methodologies for integrating explanations into end-to-end, human-in-the-loop systems. This position paper argues that the machine learning community must pivot from ad-hoc XAI methods toward addressing foundational & structural challenges, including unclear problem formulations, underspecified evaluation objectives, and the absence of pipelines for explanation-driven feedback. We support this claim through an analysis of recent ICML, NeurIPS, and ICLR papers and a survey of XAI practitioners, revealing recurring issues that limit cumulative progress. We conclude by outlining a practical checklist designed to shift XAI toward a more human-centered, action-oriented paradigm. By emphasizing foundational clarity over the development of ad-hoc methods, we hope to provide a roadmap for integrating explanations into actionable, feedback-driven AI systems.
View details
