Reliable and Responsible Foundation Models: A Comprehensive Survey

TL;DR

This comprehensive survey reviews the development, challenges, and future directions of foundation models, emphasizing reliability, responsibility, and ethical considerations across various AI domains.

Contribution

It provides an extensive overview of issues like bias, fairness, security, and explainability, and discusses methods for ensuring trustworthy foundation models.

Findings

Current state of bias and fairness mitigation

Methods for detecting AI-generated content

Future research directions in model reliability

Abstract

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.