Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2502.12145 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911078916554752 |
|---|---|
| author | Su, Jinyan Healey, Jennifer Nakov, Preslav Cardie, Claire |
| author_facet | Su, Jinyan Healey, Jennifer Nakov, Preslav Cardie, Claire |
| contents | Retrieval-Augmented Generation (RAG) has emerged as a powerful approach to mitigate large language model (LLM) hallucinations by incorporating external knowledge retrieval. However, existing RAG frameworks often apply retrieval indiscriminately,leading to inefficiencies-over-retrieving when unnecessary or failing to retrieve iteratively when required for complex reasoning. Recent adaptive retrieval strategies, though adaptively navigates these retrieval strategies, predict only based on query complexity and lacks user-driven flexibility, making them infeasible for diverse user application needs. In this paper, we introduce a novel user-controllable RAG framework that enables dynamic adjustment of the accuracy-cost trade-off. Our approach leverages two classifiers: one trained to prioritize accuracy and another to prioritize retrieval efficiency. Via an interpretable control parameter $α$, users can seamlessly navigate between minimal-cost retrieval and high-accuracy retrieval based on their specific requirements. We empirically demonstrate that our approach effectively balances accuracy, retrieval cost, and user controllability, making it a practical and adaptable solution for real-world applications. Code is available at https://github.com/JinyanSu1/Flare-Aug. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12145 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control Su, Jinyan Healey, Jennifer Nakov, Preslav Cardie, Claire Information Retrieval Artificial Intelligence Retrieval-Augmented Generation (RAG) has emerged as a powerful approach to mitigate large language model (LLM) hallucinations by incorporating external knowledge retrieval. However, existing RAG frameworks often apply retrieval indiscriminately,leading to inefficiencies-over-retrieving when unnecessary or failing to retrieve iteratively when required for complex reasoning. Recent adaptive retrieval strategies, though adaptively navigates these retrieval strategies, predict only based on query complexity and lacks user-driven flexibility, making them infeasible for diverse user application needs. In this paper, we introduce a novel user-controllable RAG framework that enables dynamic adjustment of the accuracy-cost trade-off. Our approach leverages two classifiers: one trained to prioritize accuracy and another to prioritize retrieval efficiency. Via an interpretable control parameter $α$, users can seamlessly navigate between minimal-cost retrieval and high-accuracy retrieval based on their specific requirements. We empirically demonstrate that our approach effectively balances accuracy, retrieval cost, and user controllability, making it a practical and adaptable solution for real-world applications. Code is available at https://github.com/JinyanSu1/Flare-Aug. |
| title | Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2502.12145 |