不增加参数量，用投影+门控适配器消除大模型推荐中的偏见
Lightweight Fairness for LLM-Based Recommendations via Kernelized Projection and Gated Adapters
- 用核化投影无参数移除敏感属性特征
- 在两个数据集上显著降低属性泄露且推荐精度不降
- 适合需要轻量化公平性保障的推荐系统应用
大语言模型为推荐系统带来动态、上下文感知和对话式推荐能力，但其预训练数据中的社会偏见可能被继承甚至放大，尤其当存在人口统计线索时。现有公平性解决方案要么需要额外参数微调，要么存在优化不稳定性。本文提出一种轻量级可扩展的偏见缓解方法，结合核化迭代零空间投影（INLP）与门控专家混合（MoE）适配器。该方法通过闭式解投影，无需额外可训练参数即可从大模型表示中去除单一或多敏感属性。为保留任务有效性，引入两级MoE适配器，选择性恢复有用信号而不重新引入偏见。在两个公开数据集上的实验表明，该方法在多个受保护变量上显著降低属性泄露，同时保持具有竞争力的推荐准确率。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have introduced new capabilities to recommender systems, enabling dynamic, context-aware, and conversational recommendations. However, LLM-based recommender systems inherit and may amplify social biases embedded in their pre-training data, especially when demographic cues are present. Existing fairness solutions either require extra parameters fine-tuning, or suffer from optimization instability. We propose a lightweight and scalable bias mitigation method that combines a kernelized Iterative Null-space Projection (INLP) with a gated Mixture-of-Experts (MoE) adapter. Our approach estimates a closed-form projection that removes single or multiple sensitive attributes from LLM representations with no additional trainable parameters. To preserve task utility, we introduce a two-level MoE adapter that selectively restores useful signals without reintroducing bias. Experiments on two public datasets show that our method reduces attribute leakage across multiple protected variables while maintaining competitive recommendation accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。