paper-with-me

홈 › Papers

FSGR: Mitigating Token Frequency Bias for Fair SID-Based Generative Recommendation

2026-08-13 · Yuchen Zheng, Sihan Xu, Jingwen Yang, Xiangrui Cai, Haiwei Zhang, Xiaojie Yuan arxiv

Semantic ID (SID)-based generative recommendation has recently achieved remarkable success. However, existing methods suffer from a previously overlooked fairness issue, which we term \textbf{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 \textbf{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.

📄 PDF Abstract BibTeX arXiv:2608.12845

Code (2)

HaFred/awesome-generative-recsys ★ 8
arxivsub/arXivSub_daily_arxiv ★ 4

Similar Papers 제목 키워드 기반

The Fair Language Model Paradox

2024-10-15 · Andrea Pinto, Tomer Galanti, Randall Balestriero

Large Language Models (LLMs) are widely deployed in real-world applications, yet little is known about their training dynamics at the token level. Evaluation typically relies on aggregated training loss, measured at the …

FairnessLanguage ModelingLanguage Modellingmodel

Mitigating Frequency Bias and Anisotropy in Language Model Pre-Training with Syntactic Smoothing

2024-10-15 · Richard Diehl Martinez, Zebulon Goriely, Andrew Caines, Paula Buttery 외

Language models strongly rely on frequency information because they maximize the likelihood of tokens during pre-training. As a consequence, language models tend to not generalize well to tokens that are seldom seen duri…

Language ModelingLanguage ModellingSentence

FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection

2023-09-13 · Tongkun Liu, Bing Li, Xiao Du, Bingke Jiang 외

Image reconstruction-based anomaly detection models are widely explored in industrial visual inspection. However, existing models usually suffer from the trade-off between normal reconstruction fidelity and abnormal reco…

Anomaly DetectionDefect DetectionImage ReconstructionImage Restoration

BiasFilter: An Inference-Time Debiasing Framework for Large Language Models

2025-05-28 · Xiaoqing Cheng, Ruizhe Chen, Hongying Zan, Yuxiang Jia 외

Mitigating social bias in large language models (LLMs) has become an increasingly important research objective. However, existing debiasing methods often incur high human and computational costs, exhibit limited effectiv…

Fairness

REFER: Mitigating Bias in Opinion Summarisation via Frequency Framed Prompting

2025-09-19 · Nannan Huang, Haytham M. Fayek, Xiuzhen Zhang arxiv

Individuals express diverse opinions, a fair summary should represent these viewpoints comprehensively. Previous research on fairness in opinion summarisation using large language models (LLMs) relied on hyperparameter t…