Magnus Gray Data-verified

Affiliation confirmed via AI analysis of OpenAlex, ORCID, and web sources.

Researcher

Last publication 2025 Last refreshed 2026-05-16

faculty

6 h-index 14 pubs 83 cited

Biography and Research Information

OverviewAI-generated summary

Magnus Gray's research focuses on the application of artificial intelligence (AI) and natural language processing (NLP) within regulatory science, particularly concerning drug labeling and the identification and mitigation of bias in AI models. He has investigated methods for integrating large language models (LLMs) into regulatory environments to enhance transparency and trustworthiness, using drug labeling documents as a case study. Gray's work includes developing frameworks for classifying free text in regulatory documents and benchmarking bias in healthcare AI models, employing techniques such as SD-WEAT to measure bias across sensitive populations. His research also explores the comparative performance of molecular descriptors and AI-based embeddings for toxicity prediction. Gray has published extensively on these topics, with a recent focus on bias assessment in language embedding models and the application of NLP to drug labeling text mining. His scholarship metrics include an h-index of 6, with 14 total publications and 78 citations. He collaborates with researchers from the National Center for Toxicological Research, including Leihong Wu and Joshua Xu, and Mariofanna Milanova from the University of Arkansas at Little Rock.

Metrics

  • h-index: 6
  • Publications: 14
  • Citations: 83

Selected Publications

  • Comparative Study of Molecular Descriptors and AI-Based Embeddings for Toxicity Prediction (2025)
  • Benchmarking bias in embeddings of healthcare AI models: using SD-WEAT for detection and measurement across sensitive populations (2025)
    1 citation DOI OpenAlex
  • Enhancing Bias Assessment for Complex Term Groups in Language Embedding Models: Quantitative Comparison of Methods (2024)
    2 citations DOI OpenAlex
  • SD-WEAT: Towards Robustly Measuring Bias in Input Embeddings (2024)
  • A framework enabling LLMs into regulatory environment for transparency and trustworthiness and its application to drug labeling document (2024)
    11 citations DOI OpenAlex
  • RxBERT: Enhancing drug labeling text mining and analysis with AI language modeling (2023)
    12 citations DOI OpenAlex
  • Measurement and Mitigation of Bias in Artificial Intelligence: A Narrative Literature Review for Regulatory Science (2023)
    26 citations DOI OpenAlex
  • Classifying Free Texts Into Predefined Sections Using AI in Regulatory Documents: A Case Study with Drug Labeling Documents (2023)
    8 citations DOI OpenAlex

View all publications on OpenAlex →

Collaboration Network

12 Collaborators 7 Institutions 1 Country

Top Collaborators

View profile →
View profile →
View profile →
View profile →

Similar Researchers

Based on overlapping research topics