Designing Social Robots with Ethical, User-Adaptive Explainability in the Era of Foundation Models

TL;DR

This paper emphasizes the importance of ethical, user-adaptive explainability in social robots powered by foundation models, proposing design strategies to address challenges of transparency and personalization.

Contribution

It introduces a framework for integrating ethical, user-specific explanations in foundation-model-driven social robots, with practical recommendations and a real-world use case.

Findings

Identified key challenges in explainability and ethics for adaptive social robots.

Proposed four design recommendations for personalized, modality-aware explanations.

Demonstrated applicability through a socially assistive robot use case.

Abstract

Foundation models are increasingly embedded in social robots, mediating not only what they say and do but also how they adapt to users over time. This shift renders traditional ``one-size-fits-all'' explanation strategies especially problematic: generic justifications are now wrapped around behaviour produced by models trained on vast, heterogeneous, and opaque datasets. We argue that ethical, user-adapted explainability must be treated as a core design objective for foundation-model-driven social robotics. We first identify open challenges around explainability and ethical concerns that arise when both adaptation and explanation are delegated to foundation models. Building on this analysis, we propose four recommendations for moving towards user-adapted, modality-aware, and co-designed explanation strategies grounded in smaller, fairer datasets. An illustrative use case of an LLM-driven socially assistive robot demonstrates how these recommendations might be instantiated in a sensitive, real-world domain.