E2E-AFG: An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generation

TL;DR

This paper introduces E2E-AFG, an end-to-end retrieval-augmented generation model with adaptive filtering that improves relevance and accuracy by jointly judging answer existence and generating responses, outperforming baselines.

Contribution

The paper presents a novel integrated framework that combines answer existence judgment with text generation for better retrieval-augmented language modeling.

Findings

Consistently outperforms baseline models across six datasets.

Effectively reduces irrelevant information in generated responses.

Demonstrates robustness and improved accuracy in knowledge-intensive tasks.

Abstract

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.