用动态提示和置信区间，让大模型推荐更公平。
FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems
- 结合置信区间与自适应提示，自动收紧公平性约束
- 在电影和电商数据集上减少95.5%的公平性违规
- 无需重训练模型，就能降低重复的群体偏见
我们提出 FACTER，一种面向大模型推荐系统的公平性感知框架，融合置信预测与动态提示工程。通过引入自适应语义方差阈值和违规触发机制，当检测到偏见模式时自动收紧公平性约束。我们还设计了一个对抗性提示生成器，利用历史违规信息减少重复的群体偏见，且无需重新训练大模型。在 MovieLens 和 Amazon 数据集上的实验表明，FACTER 显著降低了公平性违规（最多达 95.5%），同时保持了强推荐准确率，揭示了语义方差作为偏见有效代理指标的潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。