Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home
Viktor Moskvoretskii, Maria Marina, Mikhail Salnikov, Nikolay Ivanov, Sergey Pletenev, Daria Galimzianova, Nikita Krayko, Vasily Konovalov
Abstract
Retrieval Augmented Generation (RAG) improves correctness of Question Answering (QA) and addresses hallucinations in Large Language Models (LLMs), yet greatly increase computational costs. Besides, RAG is not always needed as may introduce irrelevant information. Recent adaptive retrieval methods integrate LLMs’ intrinsic knowledge with external information appealing to LLM self-knowledge, but they often neglect efficiency evaluations and comparisons with uncertainty estimation techniques. We bridge this gap by conducting a comprehensive analysis of 35 adaptive retrieval methods, including 8 recent approaches and 27 uncertainty estimation techniques, across 6 datasets using 10 metrics for QA performance, self-knowledge, and efficiency. Our findings show that uncertainty estimation techniques often outperform complex pipelines in terms of efficiency and self-knowledge, while maintaining comparable QA performance.
BibTeX
@inproceedings{moskvoretskii-etal-2025-adaptive,
title = "Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home",
author = "Moskvoretskii, Viktor and
Marina, Maria and
Salnikov, Mikhail and
Ivanov, Nikolay and
Pletenev, Sergey and
Galimzianova, Daria and
Krayko, Nikita and
Konovalov, Vasily and
Nikishina, Irina and
Panchenko, Alexander",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.319/",
doi = "10.18653/v1/2025.acl-long.319",
pages = "6355--6384",
ISBN = "979-8-89176-251-0"
}