LLM-Independent Adaptive RAG: Let the Question Speak for Itself
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908352729055232 |
|---|---|
| author | Marina, Maria Ivanov, Nikolay Pletenev, Sergey Salnikov, Mikhail Galimzianova, Daria Krayko, Nikita Konovalov, Vasily Panchenko, Alexander Moskvoretskii, Viktor |
| author_facet | Marina, Maria Ivanov, Nikolay Pletenev, Sergey Salnikov, Mikhail Galimzianova, Daria Krayko, Nikita Konovalov, Vasily Panchenko, Alexander Moskvoretskii, Viktor |
| contents | Large Language Models~(LLMs) are prone to hallucinations, and Retrieval-Augmented Generation (RAG) helps mitigate this, but at a high computational cost while risking misinformation. Adaptive retrieval aims to retrieve only when necessary, but existing approaches rely on LLM-based uncertainty estimation, which remain inefficient and impractical. In this study, we introduce lightweight LLM-independent adaptive retrieval methods based on external information. We investigated 27 features, organized into 7 groups, and their hybrid combinations. We evaluated these methods on 6 QA datasets, assessing the QA performance and efficiency. The results show that our approach matches the performance of complex LLM-based methods while achieving significant efficiency gains, demonstrating the potential of external information for adaptive retrieval. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04253 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM-Independent Adaptive RAG: Let the Question Speak for Itself Marina, Maria Ivanov, Nikolay Pletenev, Sergey Salnikov, Mikhail Galimzianova, Daria Krayko, Nikita Konovalov, Vasily Panchenko, Alexander Moskvoretskii, Viktor Computation and Language Machine Learning Large Language Models~(LLMs) are prone to hallucinations, and Retrieval-Augmented Generation (RAG) helps mitigate this, but at a high computational cost while risking misinformation. Adaptive retrieval aims to retrieve only when necessary, but existing approaches rely on LLM-based uncertainty estimation, which remain inefficient and impractical. In this study, we introduce lightweight LLM-independent adaptive retrieval methods based on external information. We investigated 27 features, organized into 7 groups, and their hybrid combinations. We evaluated these methods on 6 QA datasets, assessing the QA performance and efficiency. The results show that our approach matches the performance of complex LLM-based methods while achieving significant efficiency gains, demonstrating the potential of external information for adaptive retrieval. |
| title | LLM-Independent Adaptive RAG: Let the Question Speak for Itself |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2505.04253 |