A Comprehensive Survey of Bias in LLMs: Current Landscape and Future Directions
It addresses the problem of bias in LLMs for researchers, practitioners, and policymakers, but is incremental as it synthesizes existing research without new empirical results.
This paper provides a comprehensive survey of biases in Large Language Models (LLMs), reviewing their types, sources, impacts, and mitigation strategies to serve as a foundational resource for stakeholders.
Large Language Models(LLMs) have revolutionized various applications in natural language processing (NLP) by providing unprecedented text generation, translation, and comprehension capabilities. However, their widespread deployment has brought to light significant concerns regarding biases embedded within these models. This paper presents a comprehensive survey of biases in LLMs, aiming to provide an extensive review of the types, sources, impacts, and mitigation strategies related to these biases. We systematically categorize biases into several dimensions. Our survey synthesizes current research findings and discusses the implications of biases in real-world applications. Additionally, we critically assess existing bias mitigation techniques and propose future research directions to enhance fairness and equity in LLMs. This survey serves as a foundational resource for researchers, practitioners, and policymakers concerned with addressing and understanding biases in LLMs.