Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914482280726528 |
|---|---|
| author | Feng, Jun Tang, Jiahui He, Zhicheng Lv, Hang Gu, Hongchao Wang, Hao Yang, Xuezhi Fang, Shuai |
| author_facet | Feng, Jun Tang, Jiahui He, Zhicheng Lv, Hang Gu, Hongchao Wang, Hao Yang, Xuezhi Fang, Shuai |
| contents | Adaptive Retrieval-Augmented Generation aims to mitigate the interference of extraneous noise by dynamically determining the necessity of retrieving supplementary passages. However, as Large Language Models evolve with increasing robustness to noise, the necessity of adaptive retrieval warrants re-evaluation. In this paper, we rethink this necessity and propose AdaRankLLM, a novel adaptive retrieval framework. To effectively verify the necessity of adaptive listwise reranking, we first develop an adaptive ranker employing a zero-shot prompt with a passage dropout mechanism, and compare its generation outcomes against static fixed-depth retrieval strategies. Furthermore, to endow smaller open-source LLMs with this precise listwise ranking and adaptive filtering capability, we introduce a two-stage progressive distillation paradigm enhanced by data sampling and augmentation techniques. Extensive experiments across three datasets and eight LLMs demonstrate that AdaRankLLM consistently achieves optimal performance in most scenarios with significantly reduced context overhead. Crucially, our analysis reveals a role shift in adaptive retrieval: it functions as a critical noise filter for weaker models to overcome their limitations, while serving as a cost-effective efficiency optimizer for stronger reasoning models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_15621 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking Feng, Jun Tang, Jiahui He, Zhicheng Lv, Hang Gu, Hongchao Wang, Hao Yang, Xuezhi Fang, Shuai Information Retrieval Artificial Intelligence Computation and Language Adaptive Retrieval-Augmented Generation aims to mitigate the interference of extraneous noise by dynamically determining the necessity of retrieving supplementary passages. However, as Large Language Models evolve with increasing robustness to noise, the necessity of adaptive retrieval warrants re-evaluation. In this paper, we rethink this necessity and propose AdaRankLLM, a novel adaptive retrieval framework. To effectively verify the necessity of adaptive listwise reranking, we first develop an adaptive ranker employing a zero-shot prompt with a passage dropout mechanism, and compare its generation outcomes against static fixed-depth retrieval strategies. Furthermore, to endow smaller open-source LLMs with this precise listwise ranking and adaptive filtering capability, we introduce a two-stage progressive distillation paradigm enhanced by data sampling and augmentation techniques. Extensive experiments across three datasets and eight LLMs demonstrate that AdaRankLLM consistently achieves optimal performance in most scenarios with significantly reduced context overhead. Crucially, our analysis reveals a role shift in adaptive retrieval: it functions as a critical noise filter for weaker models to overcome their limitations, while serving as a cost-effective efficiency optimizer for stronger reasoning models. |
| title | Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking |
| topic | Information Retrieval Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2604.15621 |