朝向可信賴的檢索增強生成大型語言模型：一項調查

Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey

February 8, 2025

作者: Bo Ni, Zheyuan Liu, Leyao Wang, Yongjia Lei, Yuying Zhao, Xueqi Cheng, Qingkai Zeng, Luna Dong, Yinglong Xia, Krishnaram Kenthapadi, Ryan Rossi, Franck Dernoncourt, Md Mehrab Tanjim, Nesreen Ahmed, Xiaorui Liu, Wenqi Fan, Erik Blasch, Yu Wang, Meng Jiang, Tyler Derr

cs.AI

摘要

檢索增強生成（RAG）是一項先進技術，旨在應對人工智慧生成內容（AIGC）的挑戰。通過將上下文檢索整合到內容生成中，RAG 提供可靠且最新的外部知識，減少幻覺，確保在各種任務中相關的上下文。然而，儘管 RAG 取得了成功並展現了潛力，最近的研究顯示 RAG 范式也帶來了新的風險，包括韌性問題、隱私擔憂、對抗性攻擊和責任問題。解決這些風險對於未來的 RAG 系統應用至關重要，因為這些風險直接影響其可信度。儘管已經開發了各種方法來提高 RAG 方法的可信度，但在這一主題的研究中缺乏統一的觀點和框架。因此，在本文中，我們旨在通過提供一份全面的發展可信 RAG 系統的路線圖來填補這一空白。我們將討論圍繞五個關鍵觀點展開：可靠性、隱私、安全性、公平性、可解釋性和責任性。對於每個觀點，我們提出一個通用框架和分類法，提供了一種結構化方法來理解當前挑戰，評估現有解決方案，並確定有前途的未來研究方向。為了鼓勵更廣泛的應用和創新，我們還強調了可信 RAG 系統對下游應用的重大影響。

English

Retrieval-Augmented Generation (RAG) is an advanced technique designed to address the challenges of Artificial Intelligence-Generated Content (AIGC). By integrating context retrieval into content generation, RAG provides reliable and up-to-date external knowledge, reduces hallucinations, and ensures relevant context across a wide range of tasks. However, despite RAG's success and potential, recent studies have shown that the RAG paradigm also introduces new risks, including robustness issues, privacy concerns, adversarial attacks, and accountability issues. Addressing these risks is critical for future applications of RAG systems, as they directly impact their trustworthiness. Although various methods have been developed to improve the trustworthiness of RAG methods, there is a lack of a unified perspective and framework for research in this topic. Thus, in this paper, we aim to address this gap by providing a comprehensive roadmap for developing trustworthy RAG systems. We place our discussion around five key perspectives: reliability, privacy, safety, fairness, explainability, and accountability. For each perspective, we present a general framework and taxonomy, offering a structured approach to understanding the current challenges, evaluating existing solutions, and identifying promising future research directions. To encourage broader adoption and innovation, we also highlight the downstream applications where trustworthy RAG systems have a significant impact.