FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems

TL;DR

FACTER is a novel framework that enhances fairness in LLM-based recommender systems by combining conformal prediction, adaptive prompt engineering, and adversarial techniques to reduce bias while maintaining accuracy.

Contribution

The paper introduces FACTER, a new fairness-aware framework that dynamically adjusts fairness constraints and employs adversarial prompt generation without retraining the LLM.

Findings

Reduces fairness violations by up to 95.5%.

Maintains strong recommendation accuracy.

Identifies semantic variance as a key bias proxy.

Abstract

We propose FACTER, a fairness-aware framework for LLM-based recommendation systems that integrates conformal prediction with dynamic prompt engineering. By introducing an adaptive semantic variance threshold and a violation-triggered mechanism, FACTER automatically tightens fairness constraints whenever biased patterns emerge. We further develop an adversarial prompt generator that leverages historical violations to reduce repeated demographic biases without retraining the LLM. Empirical results on MovieLens and Amazon show that FACTER substantially reduces fairness violations (up to 95.5%) while maintaining strong recommendation accuracy, revealing semantic variance as a potent proxy of bias.