Saved in:
Bibliographic Details
Main Authors: Jiang, Yun, Xie, Zilong, Zhang, Wei, Fang, Yun, Pan, Shuai
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.00437
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915276731187200
author Jiang, Yun
Xie, Zilong
Zhang, Wei
Fang, Yun
Pan, Shuai
author_facet Jiang, Yun
Xie, Zilong
Zhang, Wei
Fang, Yun
Pan, Shuai
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00437
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle E2E-AFG: An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generation
Jiang, Yun
Xie, Zilong
Zhang, Wei
Fang, Yun
Pan, Shuai
Computation and Language
Artificial Intelligence
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.
title E2E-AFG: An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2411.00437