# When to Retrieve: Teaching LLMs to Utilize Information Retrieval Effectively

arXiv: https://arxiv.org/abs/2404.19705 · HTML: https://mlsanity.com/paper/2404.19705/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 46 references that are in the map.
- First posted on arXiv 30 Apr 2024.

## Builds on (most cited first, 30 of 30)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [QuAC : Question Answering in Context](https://mlsanity.com/paper/1808.07036/) (2018)
- [Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering](https://mlsanity.com/paper/2101.00774/) (2021)
- [Seven Failure Points When Engineering a Retrieval Augmented Generation System](https://mlsanity.com/paper/2401.05856/) (2024)
- [Two-Step Question Retrieval for Open-Domain QA](https://mlsanity.com/paper/2205.09393/) (2022)
- [Navigating Uncertainty: Optimizing API Dependency for Hallucination Reduction in Closed-Book Question Answering](https://mlsanity.com/paper/2401.01780/) (2024)

## Built on by (most cited first, 21 of 21)

- [Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation](https://mlsanity.com/paper/2501.02226/) (2025)
- [DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios](https://mlsanity.com/paper/2510.15501/) (2025)
- [Towards Reliable Medical Question Answering: Techniques and Challenges in Mitigating Hallucinations in Language Models](https://mlsanity.com/paper/2408.13808/) (2024)
- [Retrieval-Enhanced Machine Learning: Synthesis and Opportunities](https://mlsanity.com/paper/2407.12982/) (2024)
- [Wait, that's not an option: LLMs Robustness with Incorrect Multiple-Choice Options](https://mlsanity.com/paper/2409.00113/) (2024)
- [Bridging Legal Knowledge and AI: Retrieval-Augmented Generation with Vector Stores, Knowledge Graphs, and Hierarchical Non-negative Matrix Factorization](https://mlsanity.com/paper/2502.20364/) (2025)
- [ECoRAG: Evidentiality-guided Compression for Long Context RAG](https://mlsanity.com/paper/2506.05167/) (2025)
- [Distilling the Thought, Watermarking the Answer: A Principle Semantic Guided Watermark for Large Reasoning Models](https://mlsanity.com/paper/2601.05144/) (2026)
- [Quantifying Memorization and Parametric Response Rates in Retrieval-Augmented Vision-Language Models](https://mlsanity.com/paper/2502.13836/) (2025)
- [SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models](https://mlsanity.com/paper/2502.14908/) (2025)
- [Agent-Enhanced Large Language Models for Researching Political Institutions](https://mlsanity.com/paper/2503.13524/) (2025)
- [LLMs on a Budget? Say HOLA](https://mlsanity.com/paper/2506.18952/) (2025)
- [HF-RAG: Hierarchical Fusion-based RAG with Multiple Sources and Rankers](https://mlsanity.com/paper/2509.02837/) (2025)
- [HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering](https://mlsanity.com/paper/2509.09713/) (2025)
- [WaterMoE: Expert-Routing-based Watermarking for High Fidelity and Efficiency](https://mlsanity.com/paper/2607.13099/) (2026)
- [Dual-Layer Agentic Memory with Fast Write Routing and Slow Consolidation](https://mlsanity.com/paper/2608.22215/) (2026)
- [SALMONN-duo: Adaptive Dual-System Coordination for Full-Duplex Voice Agents](https://mlsanity.com/paper/2609.34247/) (2026)
- [Let your LLM generate a few tokens and you will reduce the need for retrieval](https://mlsanity.com/paper/2412.11536/) (2024)
- [Mask-to-Correct^+: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction](https://mlsanity.com/paper/2605.18776/) (2026)
- [Why Didn't It Check? Unsupported Final Claims and Their Repair in Two Tool-Equipped Language Models](https://mlsanity.com/paper/2608.27768/) (2026)
- [Trustworthy Domain-Specific AI for Structured Knowledge Retrieval and Reasoning](https://mlsanity.com/paper/2610.08894/) (2026)

## Abstract (arXiv)

In this paper, we demonstrate how Large Language Models (LLMs) can effectively learn to use an off-the-shelf information retrieval (IR) system specifically when additional context is required to answer a given question. Given the performance of IR systems, the optimal strategy for question answering does not always entail external information retrieval; rather, it often involves leveraging the parametric memory of the LLM itself. Prior research has identified this phenomenon in the PopQA dataset, wherein the most popular questions are effectively addressed using the LLM's parametric memory, while less popular ones require IR system usage. Following this, we propose a tailored training approach for LLMs, leveraging existing open-domain question answering datasets. Here, LLMs are trained to generate a special token, <RET>, when they do not know the answer to a question. Our evaluation of the Adaptive Retrieval LLM (Adapt-LLM) on the PopQA dataset showcases improvements over the same LLM under three configurations: (i) retrieving information for all the questions, (ii) using always the parametric memory of the LLM, and (iii) using a popularity threshold to decide when to use a retriever. Through our analysis, we demonstrate that Adapt-LLM is able to generate the <RET> token when it determines that it does not know how to answer a question, indicating the need for IR, while it achieves notably high accuracy levels when it chooses to rely only on its parametric memory.