AI Fairness Metrics: A Curated Reading List by Theoretical Foundation

This curated reading list compiles 32 influential papers and texts on AI fairness metrics, organised by theoretical foundation across eight thematic areas: surveys and introductory frameworks, group fairness, individual fairness, causal and counterfactual fairness, impossibility theorems and trade-offs, fairness in large language models and generative AI, domain-specific applications, and bias mitigation methods. Each entry includes a structured annotation and keyword tags. The list is intended as a navigational resource for researchers, practitioners, and students entering the field. A companion article is available on Medium. https://medium.com/@hairufan/the-ai-fairness-problem-is-more-complicated-than-you-think-heres-where-to-start-reading-6a29c97a9379