FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems
This addresses fairness problems in LLM-based recommender systems for users, though it appears incremental as it builds on existing conformal prediction and prompt engineering techniques.
The paper tackles fairness issues in LLM-based recommendation systems by proposing FACTER, a framework that combines conformal prediction with dynamic prompt engineering to automatically tighten fairness constraints when biased patterns emerge. Results on MovieLens and Amazon datasets show it reduces fairness violations by up to 95.5% while maintaining strong recommendation accuracy.
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.