Building Trustworthy AI for Materials Discovery: From Autonomous Laboratories to Z-scores

2025-11-30

AI Summary

AI/ML models in materials discovery suffer from insufficient generalizability, interpretability, fairness, transparency, robustness, and stability, compounded by the absence of a systematic framework for trustworthiness assessment. To address this gap, we propose GIFTERS—the first seven-dimensional trustworthy AI evaluation framework specifically designed for materials science. GIFTERS integrates Bayesian modeling, uncertainty quantification, and cross-domain trustworthy AI techniques transferable from domains such as healthcare and climate science. Comprehensive evaluation reveals critical weaknesses in fairness and interpretability across current models, with median scores of only 5/7. Beyond providing quantitative diagnostic benchmarks, GIFTERS establishes a closed-loop pathway from assessment to model improvement, thereby enabling human–AI collaborative paradigms for trustworthy materials discovery.

Technology Category

• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Machine Learning: Calibration & Uncertainty Quantification
• Humans and AI: AI for Accessibility

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Accelerated material discovery increasingly relies on artificial intelligence and machine learning, collectively termed "AI/ML". A key challenge in using AI is ensuring that human scientists trust the models are valid and reliable. Accordingly, we define a trustworthy AI framework GIFTERS for materials science and discovery to evaluate whether reported machine learning methods are generalizable, interpretable, fair, transparent, explainable, robust, and stable. Through a critical literature review, we highlight that these are the trustworthiness principles most valued by the materials discovery community. However, we also find that comprehensive approaches to trustworthiness are rarely reported; this is quantified by a median GIFTERS score of 5/7. We observe that Bayesian studies frequently omit fair data practices, while non-Bayesian studies most frequently omit interpretability. Finally, we identify approaches for improving trustworthiness methods in artificial intelligence and machine learning for materials science by considering work accomplished in other scientific disciplines such as healthcare, climate science, and natural language processing with an emphasis on methods that may transfer to materials discovery experiments. By combining these observations, we highlight the necessity of human-in-the-loop, and integrated approaches to bridge the gap between trustworthiness and uncertainty quantification for future directions of materials science research. This ensures that AI/ML methods not only accelerate discovery, but also meet ethical and scientific norms established by the materials discovery community. This work provides a road map for developing trustworthy artificial intelligence systems that will accurately and confidently enable material discovery.

Problem

• Developing trustworthy AI framework for materials discovery validation
• Addressing trust gaps in AI models through comprehensive evaluation metrics
• Bridging trustworthiness principles with uncertainty quantification in materials science

Innovation

• Framework GIFTERS evaluates AI trustworthiness principles
• Human-in-the-loop integrates trust with uncertainty quantification
• Cross-disciplinary methods transfer to improve materials discovery AI