FAIDER: Fairness-Aware Item-Level Decoding for Large Language Model Recommenders

Ziwei Wu, Jingrui He

Abstract

Large language model (LLM) recommenders can produce semantically different recommendations when a user's protected attribute changes, even if the interaction history remains fixed. Controlling this disparity is challenging when model weights and full-vocabulary logits are inaccessible. We propose FAIDER (Fairness-Aware Item-level DEcoding for Recommendation), which incorporates fairness into list construction by selecting complete item candidates rather than manipulating token-level logits or repeatedly repairing finished outputs. The central idea is to separate the operational criterion for a violation from how strongly generation is constrained. Conformal-inspired empirical calibration fixes a cross-group semantic-disparity threshold, while online decoding applies either hard filtering or a soft penalty adjusted through dual-inspired feedback to target a prescribed violation rate. Separately, we establish a pathwise guarantee: under a uniform enforceability assumption, the soft decoder's empirical violation rate exceeds its target by at most $O(1/T)$. Experiments across recommendation benchmarks and LLM backbones show that Soft FAIDER improves both measured semantic fairness and ranking quality over the evaluated prompt-repair baselines. It also generally achieves a more favorable fairness-utility balance than the hard variant, indicating that stricter per-recommendation constraints do not necessarily yield lower measured disparity.
BibTeX
@misc{wu2026faider,
  author = {Ziwei Wu and Jingrui He},
  title = {{FAIDER: Fairness-Aware Item-Level Decoding for Large Language Model Recommenders}},
  year = {2026},
  eprint = {2611.10285},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.10285},
}
Figure