cs.AINov 6, 2026

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

Authors: Ziwei Wu, Jingrui He

Organizations: University of Illinois Urbana-Champaign

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)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.

Figures & tables

Explore similar work

CardsList
  1. Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders

    Aug 8, 2026Chan Aristella Lu, Arya Fayyazi, Junhao Zhang +6LLM AuditingLanguage Model Bias Evaluation

  2. Lightweight Fairness for LLM-Based Recommendations via Kernelized Projection and Gated Adapters

    Mar 24, 2026Nan Cui, Wendy Hui Wang, Yue NingFairness in Recommender SystemsDemographic Bias in Language Models

  3. Reproducing FACTER: Fairness via Conformal Thresholding and Prompt Repair

    Jun 26, 2026Oscar Miró López-Feliu, Daimy van Loo, Xanthos Kekkos +2Algorithmic FairnessConformal Prediction