Safety
FSGR: Mitigating Token Frequency Bias for Fair SID-Based Generative Recommendation
arXiv:2608.12845v1 Announce Type: cross Abstract: Semantic ID (SID)-based generative recommendation has recently achieved remarkable success. However, existing methods suffer from a previously overloo
arXiv:2608.12845v1 Announce Type: cross Abstract: Semantic ID (SID)-based generative recommendation has recently achieved remarkable success. However, existing methods suffer from a previously overlooked fairness issue, which we term extbf{Token Frequency Bias}, where high-frequency SID tokens are systematically over-predicted while low-frequency SID tokens are under-predicted. This bias originates from the combined effects of imbalanced semantic codebooks during SID construction, and popularity bias together with the maximum likelihood estimation objective during recommendation training, resulting in unfair exposure across item categories. Existing SID methods mainly focus on improving codebook quality and overlook the impact of token frequency imbalance on downstream recommendation fairness, while LLM debiasing methods often yield suboptimal results when directly applied to SID-based recommendation, due to the hierarchical semantics of SID tokens. To address this issue, we propose extbf{FSGR}, a fairness optimization framework for SID-based generative recommendation. During SID construction, FSGR employs OT-based Assignment Optimization and Dual-Criteria Re-anchor mechanism to form a more balanced SID representation space. During recommendation training, it adopts a two-stage training strategy and introduces Hierarchical Frequency Calibration for layer-specific fairness fine-tuning. Experiments on three public datasets with three backbone models demonstrate that FSGR mitigates token frequency bias and delivers an average Gini fairness improvement of over 20% while maintaining competitive recommendation accuracy.
Related
- Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching
- Deep Interest Mining with Cross-Modal Alignment for SemanticID Generation in Generative Recommendation
- LBR: Towards Mitigating Length Bias in Large Language Models for Recommendation
- TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation
Source: arXiv cs.AI | 2026-08-14