Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.05312 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909781628813312 |
|---|---|
| author | Qin, Qitao Luo, Yucong Lu, Yihang Chu, Zhibo Liu, Xiaoman Meng, Xianwei |
| author_facet | Qin, Qitao Luo, Yucong Lu, Yihang Chu, Zhibo Liu, Xiaoman Meng, Xianwei |
| contents | Retrieval-Augmented Generation (RAG), by integrating non-parametric knowledge from external knowledge bases into models, has emerged as a promising approach to enhancing response accuracy while mitigating factual errors and hallucinations. This method has been widely applied in tasks such as Question Answering (QA). However, existing RAG methods struggle with open-domain QA tasks because they perform independent retrieval operations and directly incorporate the retrieved information into generation without maintaining a summarizing memory or using adaptive retrieval strategies, leading to noise from redundant information and insufficient information integration. To address these challenges, we propose Adaptive memory-based optimization for enhanced RAG (Amber) for open-domain QA tasks, which comprises an Agent-based Memory Updater, an Adaptive Information Collector, and a Multi-granular Content Filter, working together within an iterative memory updating paradigm. Specifically, Amber integrates and optimizes the language model's memory through a multi-agent collaborative approach, ensuring comprehensive knowledge integration from previous retrieval steps. It dynamically adjusts retrieval queries and decides when to stop retrieval based on the accumulated knowledge, enhancing retrieval efficiency and effectiveness. Additionally, it reduces noise by filtering irrelevant content at multiple levels, retaining essential information to improve overall model performance. We conduct extensive experiments on several open-domain QA datasets, and the results demonstrate the superiority and effectiveness of our method and its components. The source code is available \footnote{https://anonymous.4open.science/r/Amber-B203/}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05312 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Adaptive Memory-Based Optimization for Enhanced Retrieval-Augmented Generation Qin, Qitao Luo, Yucong Lu, Yihang Chu, Zhibo Liu, Xiaoman Meng, Xianwei Information Retrieval Artificial Intelligence Retrieval-Augmented Generation (RAG), by integrating non-parametric knowledge from external knowledge bases into models, has emerged as a promising approach to enhancing response accuracy while mitigating factual errors and hallucinations. This method has been widely applied in tasks such as Question Answering (QA). However, existing RAG methods struggle with open-domain QA tasks because they perform independent retrieval operations and directly incorporate the retrieved information into generation without maintaining a summarizing memory or using adaptive retrieval strategies, leading to noise from redundant information and insufficient information integration. To address these challenges, we propose Adaptive memory-based optimization for enhanced RAG (Amber) for open-domain QA tasks, which comprises an Agent-based Memory Updater, an Adaptive Information Collector, and a Multi-granular Content Filter, working together within an iterative memory updating paradigm. Specifically, Amber integrates and optimizes the language model's memory through a multi-agent collaborative approach, ensuring comprehensive knowledge integration from previous retrieval steps. It dynamically adjusts retrieval queries and decides when to stop retrieval based on the accumulated knowledge, enhancing retrieval efficiency and effectiveness. Additionally, it reduces noise by filtering irrelevant content at multiple levels, retaining essential information to improve overall model performance. We conduct extensive experiments on several open-domain QA datasets, and the results demonstrate the superiority and effectiveness of our method and its components. The source code is available \footnote{https://anonymous.4open.science/r/Amber-B203/}. |
| title | Towards Adaptive Memory-Based Optimization for Enhanced Retrieval-Augmented Generation |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2504.05312 |