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

Arya Fayyazi, Mehdi Kamal, Massoud Pedram
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16407-16422, 2025.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-fayyazi25a, title = {{FACTER}: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair {LLM}-Based Recommender Systems}, author = {Fayyazi, Arya and Kamal, Mehdi and Pedram, Massoud}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {16407--16422}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/fayyazi25a/fayyazi25a.pdf}, url = {https://proceedings.mlr.press/v267/fayyazi25a.html}, 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.} }
Endnote
%0 Conference Paper %T FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems %A Arya Fayyazi %A Mehdi Kamal %A Massoud Pedram %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-fayyazi25a %I PMLR %P 16407--16422 %U https://proceedings.mlr.press/v267/fayyazi25a.html %V 267 %X 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.
APA
Fayyazi, A., Kamal, M. & Pedram, M.. (2025). FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:16407-16422 Available from https://proceedings.mlr.press/v267/fayyazi25a.html.

Related Material