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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Fayyazi, Arya, Kamal, Mehdi, Pedram, Massoud
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915138664136704
author Fayyazi, Arya
Kamal, Mehdi
Pedram, Massoud
author_facet Fayyazi, Arya
Kamal, Mehdi
Pedram, Massoud
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_02966
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems
Fayyazi, Arya
Kamal, Mehdi
Pedram, Massoud
Information Retrieval
Artificial Intelligence
Computers and Society
Machine Learning
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.
title FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems
topic Information Retrieval
Artificial Intelligence
Computers and Society
Machine Learning
url https://arxiv.org/abs/2502.02966