FAIDER: Fairness-Aware Item-Level Decoding for Large Language Model Recommenders
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 . 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
| Dataset | Method | Qwen3-8B | Llama3.1-8B-Instruct | ||||
|---|---|---|---|---|---|---|---|
| Recall@10 | NDCG@10 | CFR | Recall@10 | NDCG@10 | CFR | ||
| MovieLens | Zero-shot | 0.402 | 0.458 | 0.742 | 0.358 | 0.402 | 0.701 |
| UP5 | 0.381 | 0.427 | 0.613 | 0.336 | 0.374 | 0.556 | |
| FACTER | 0.389 | 0.445 | 0.591 | 0.338 | 0.382 | 0.440 | |
| Hard FAIDER | 0.382 | 0.432 | 0.389 | 0.333 | 0.371 | 0.398 | |
| Soft FAIDER | 0.390 | 0.446 | 0.474 | 0.352 | 0.397 | 0.243 | |