From Bias to Balance: Fairness-Aware Paper Recommendation for Equitable Peer Review

Researchers developed Fair-PaperRec, an AI system that uses fairness regularization to reduce bias in academic peer review processes. The system achieved up to 42% increased participation from underrepresented groups while maintaining scholarly quality with minimal utility loss.

• →Fair-PaperRec uses a Multi-Layer Perceptron with fairness loss functions to re-rank papers after double-blind review.
• →Testing on synthetic datasets demonstrated the system's robustness across varying bias levels from high to near-fair conditions.
• →Real-world validation using ACM conference data showed 42.03% increase in underrepresented group participation with only 3.16% utility change.
• →The fairness regularization acts as both an equity mechanism and quality regularizer, particularly effective in highly biased environments.
• →The framework offers a practical solution for post-review paper selection that can preserve or enhance scholarly quality while promoting inclusion.