E2E-AFG：一种用于检索增强生成的端到端自适应过滤模型
E2E-AFG: An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generation
- Advanced Institute of Information Technology, Peking University（北京大学信息技术高等研究院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出端到端自适应过滤模型E2E-AFG，将答案存在性判断与文本生成统一到同一框架中，以降低检索不相关信息的影响，并在六个知识密集型数据集上验证了其优于基线模型的效果。
AI中文摘要：
检索增强生成方法往往忽视从外部知识库检索到的内容质量，导致不相关信息或潜在错误信息对大语言模型的生成结果产生负面影响。本文提出了一种用于检索增强生成的端到端自适应过滤模型（E2E-AFG），将答案存在性判断与文本生成整合到统一的端到端框架中。这使得模型能够更有效地关注相关内容，同时减少不相关信息的影响，并生成准确的答案。我们在六个具有代表性的知识密集型语言数据集上对E2E-AFG进行了评估，结果表明该模型在所有任务上均一致优于基线模型，证明了所提方法的有效性和鲁棒性。
英文摘要：
Retrieval-augmented generation methods often neglect the quality of content retrieved from external knowledge bases, resulting in irrelevant information or potential misinformation that negatively affects the generation results of large language models. In this paper, we propose an end-to-end model with adaptive filtering for retrieval-augmented generation (E2E-AFG), which integrates answer existence judgment and text generation into a single end-to-end framework. This enables the model to focus more effectively on relevant content while reducing the influence of irrelevant information and generating accurate answers. We evaluate E2E-AFG on six representative knowledge-intensive language datasets, and the results show that it consistently outperforms baseline models across all tasks, demonstrating the effectiveness and robustness of the proposed approach.
