E2E-AFG: An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generation
This addresses the issue of retrieval quality affecting large language model outputs, though it appears incremental as an enhancement to existing methods.
The paper tackles the problem of irrelevant or misleading retrieved content in retrieval-augmented generation by proposing an end-to-end model with adaptive filtering, which outperforms baselines on six knowledge-intensive language datasets.
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.