Fundamental Information-theoretic Limitation in Explaining AI 

Date & Time

Date: Tuesday, Aug 25, 2026

Time: 2:00 -3:00 PM

Venue: IB 3106

Zoom: 789 843 9496

Speaker

Dr. SUZUKI Atsushi

The University of Hong Kong, Assistant Professor

Abstract

While large-scale models such as LLMs and diffusion models have achieved practical success, public institutions have emphasized the importance of explainability in AI. Existing methods for explaining AI, however, are not designed to provide completely faithful explanations of the behavior of large-scale AI systems. Although a completely faithful and interpretable explanation of the behavior of an AI system might be useful for AI governance, it has not been known whether providing such an explanation is theoretically possible. In this paper, we mathematically prove a fundamental quadrilemma in explaining AI, stating that AI and its explanation cannot satisfy the following four conditions simultaneously: 1) the complexity of the operation environment, 2) the goodness of the AI’s performance, 3) the interpretability of the AI’s explanation, and 4) the complete faithfulness of the AI’s explanation. This quadrilemma suggests that, in most applications where we cannot change the environment or sacrifice good AI performance and an interpretable explanation, we should give up complete faithfulness of explanations and should instead aim to explain only the parts that are important for applications. As a consequence, the quadrilemma implies that AI governance should be designed on the premise that the faithfulness of AI explanations is always incomplete. 

Bio
Atsushi Suzuki received the Ph.D. degree from the Graduate School of Information Science and Technology, The University of Tokyo, Japan, in 2020. From 2020 to 2022, Atsushi was a Lecturer with the University of Greenwich, U.K. From 2022 to 2025, Atsushi was a Lecturer with King’s College London, U.K. Since 2025, Atsushi has been an Assistant Professor with The University of Hong Kong. Atsushi’s research interests include machine learning theory using information theory, statistics, geometry, and related mathematical tools