Large Language Model (LLM)-based recommendation systems excel in delivering comprehensive suggestions by deeply analyzing content and user behavior. However, they often inherit biases from skewed training data, favoring mainstream content while underrepresenting diverse or non-traditional options. This study explores the interplay between bias and LLM-based recommendation systems, focusing on music, song, and book recommendations across diverse demographic and cultural groups. This paper analyzes bias in LLM-based recommendation systems across multiple models (GPT, LLaMA, and Gemini), revealing its deep and pervasive impact on outcomes. Intersecting identities and contextual factors, like socioeconomic status, further amplify biases, complicating fair recommendations across diverse groups. Our findings reveal that bias in these systems is deeply ingrained, yet even simple interventions like prompt engineering can significantly reduce it. We further propose a retrieval-augmented generation strategy to mitigate bias more effectively. Numerical experiments validate these strategies, demonstrating both the pervasive nature of bias and the impact of the proposed solutions.

翻译：基于大型语言模型（LLM）的推荐系统通过深度分析内容与用户行为，在提供全面建议方面表现出色。然而，它们常常继承自倾斜训练数据的偏见，倾向于主流内容，同时未能充分代表多样化或非传统的选项。本研究探讨了偏见与基于LLM的推荐系统之间的相互作用，重点关注针对不同人口统计与文化群体的音乐、歌曲和书籍推荐。本文分析了多个模型（GPT、LLaMA和Gemini）中基于LLM的推荐系统的偏见，揭示了其对推荐结果的深刻且普遍的影响。交叉身份与情境因素（如社会经济地位）进一步放大了偏见，使得在不同群体间实现公平推荐变得复杂。我们的研究结果表明，这些系统中的偏见根深蒂固，但即使是简单的干预措施（如提示工程）也能显著减少偏见。我们进一步提出了一种检索增强生成策略，以更有效地缓解偏见。数值实验验证了这些策略，既证明了偏见的普遍性，也展示了所提解决方案的成效。