Logo image
Back
Reliable and Responsible Foundation Models: A Comprehensive Survey
Preprint   Open access

Reliable and Responsible Foundation Models: A Comprehensive Survey

Xinyu Yang, Junlin Han, Rishi Bommasani, Jinqi Luo, Wenjie Qu, Wangchunshu Zhou, Adel Bibi, Xiyao Wang, Jaehong Yoon, Elias Stengel-Eskin, …
pp 1-168
04 Feb 2026
DOI: https://doi.org/10.48550/arxiv.2602.08145
url
https://doi.org/10.48550/arxiv.2602.08145View
Preprint (Author's original) Open arXiv.org - Non-exclusive license to distribute

Abstract

Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Computer Vision and Pattern Recognition Computer Science - Computers and Society Computer Science - Learning Artificial Intelligence or Cybernetics
Foundation models, including Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), Image Generative Models (i.e, Text-to-Image Models and Image-Editing Models), and Video Generative Models, have become essential tools with broad applications across various domains such as law, medicine, education, finance, science, and beyond. As these models see increasing real-world deployment, ensuring their reliability and responsibility has become critical for academia, industry, and government. This survey addresses the reliable and responsible development of foundation models. We explore critical issues, including bias and fairness, security and privacy, uncertainty, explainability, and distribution shift. Our research also covers model limitations, such as hallucinations, as well as methods like alignment and Artificial Intelligence-Generated Content (AIGC) detection. For each area, we review the current state of the field and outline concrete future research directions. Additionally, we discuss the intersections between these areas, highlighting their connections and shared challenges. We hope our survey fosters the development of foundation models that are not only powerful but also ethical, trustworthy, reliable, and socially responsible.

Metrics

3 Record Views

Related content

Is preprint of

Details

Logo image