mlsanityData to 7 Oct 2026

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

arXiv 2505.04253 ↗First posted 7 May 2025cs.CL cs.LGcited by 7

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

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.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 20 of its 39 references that are in the map. First posted on arXiv 7 May 2025.

Builds on

20 of 39 references.

References · 20

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  5. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  7. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  8. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  9. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  10. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  11. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  12. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 308
8 more
  1. 2020Unsupervised Quality Estimation for Neural Machine Translationcited by 210
  2. 2022Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answeringcited by 71
  3. 2024Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluationcited by 37
  4. 2025Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Homecited by 33
  5. 2023Knowledge-Augmented Language Model Verificationcited by 21
  6. 2023Large Language Models Meet Knowledge Graphs to Answer Factoid Questionscited by 11
  7. 2023Multilingual End to End Entity Linkingcited by 8
  8. 2024Konstruktor: A Strong Baseline for Simple Knowledge Graph Question Answeringcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 40
  2. 2025Query-Level Uncertainty in Large Language Modelscited by 12
  3. 2026RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG Routingcited by 4
  4. 2026How You Ask Matters! Adaptive RAG Robustness to Query Variationscited by 3
  5. 2025Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Rerankingcited by 0
  6. 2026Boosting Self-Consistency with Rankingcited by 0
  7. 2026Before Answering: Evidence Sufficiency under Size-Matched Memory Constructioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control
  2. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
  3. 2025When Retrieval Succeeds and Fails: Rethinking Retrieval-Augmented Generation for LLMs
  4. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Models
  5. 2023Retrieval-Augmented Generation for Large Language Models: A Survey
  6. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
  7. 2025Tuning LLMs by RAG Principles: Towards LLM-native Memory
  8. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely