没有免费午餐：检索增强生成破坏了大型语言模型的公平性，即使对于警惕的用户也是如此
No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users
AI总结：
本研究提出三级威胁模型，揭示检索增强生成（RAG）无需微调即可破坏LLM公平性对齐，即使使用完全审查的无偏见数据集仍会产生偏见输出，凸显了开发新公平性保障策略的迫切需求。
摘要：
检索增强生成（RAG）因其有效性和成本效益被广泛采用，以缓解幻觉并增强大型语言模型（LLMs）的特定领域生成能力。然而，这种有效性和成本效益真的是免费午餐吗？在本研究中，我们通过从用户对公平性认知的角度提出一个实用的三级威胁模型，全面调查了与RAG相关的公平性成本。具体而言，不同程度的用户公平性认知会导致对外部数据集进行不同程度的公平性审查。我们使用未审查、部分审查和完全审查的数据集来检验RAG的公平性影响。我们的实验表明，通过RAG可以轻易破坏公平性对齐，而无需进行微调或重新训练。即使使用完全审查且理应无偏见的外部数据集，RAG也可能导致有偏见的输出。我们的研究结果强调了当前对齐方法在基于RAG的LLMs背景下的局限性，并突出了对新策略的迫切需求以确保公平性。我们提出了潜在的缓解措施，并呼吁进一步研究以在基于RAG的LLMs中开发稳健的公平性保障措施。
英文摘要：
Retrieval-Augmented Generation (RAG) is widely adopted for its effectiveness and cost-efficiency in mitigating hallucinations and enhancing the domain-specific generation capabilities of large language models (LLMs). However, is this effectiveness and cost-efficiency truly a free lunch? In this study, we comprehensively investigate the fairness costs associated with RAG by proposing a practical three-level threat model from the perspective of user awareness of fairness. Specifically, varying levels of user fairness awareness result in different degrees of fairness censorship on the external dataset. We examine the fairness implications of RAG using uncensored, partially censored, and fully censored datasets. Our experiments demonstrate that fairness alignment can be easily undermined through RAG without the need for fine-tuning or retraining. Even with fully censored and supposedly unbiased external datasets, RAG can lead to biased outputs. Our findings underscore the limitations of current alignment methods in the context of RAG-based LLMs and highlight the urgent need for new strategies to ensure fairness. We propose potential mitigations and call for further research to develop robust fairness safeguards in RAG-based LLMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
