Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home

Viktor Moskvoretskii, Maria Lysyuk, Mikhail Salnikov, Nikolay Ivanov, Sergey Pletenev +5 more
1/22/2025
cs.CLcs.LG

No official code found. Best implementation: s-nlp/AdaRAGUE (21 stars, MIT, last commit 2025-05-17).

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.

View on arXivView PDF

Code Implementations(1)

s-nlp/AdaRAGUECommunity65%
MIT

[ACL 2025] Adaptive Retrieval without Self-Knowledge? Bringing Uncertainty Back Home

214C, C++Feb 18, 20251 years agoMIT
llmrag

Similar Papers

LLM-Independent Adaptive RAG: Let the Question Speak for Itself

90% match2025

To Retrieve or Not to Retrieve? Uncertainty Detection for Dynamic Retrieval Augmented Generation

89% match2025

SUGAR: Leveraging Contextual Confidence for Smarter Retrieval

88% match2025

SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation

87% match1 repo432024

Query-Level Uncertainty in Large Language Models

86% match2025

When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation

86% match1 repo252024

Cite this paper

@article{moskvoretskii2025adaptive,
  title  = {Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home},
  author = {Viktor Moskvoretskii and Maria Lysyuk and Mikhail Salnikov and Nikolay Ivanov and Sergey Pletenev and Daria Galimzianova and Nikita Krayko and Vasily Konovalov and Irina Nikishina and Alexander Panchenko},
  year   = {2025},
  eprint = {2501.12835},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.12835v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.12835.svg)](https://codeofpaper.com/paper/2501.12835)

Discussion