# Retrieval Helps or Hurts? A Deeper Dive into the Efficacy of Retrieval Augmentation to Language Models

arXiv: https://arxiv.org/abs/2402.13492 · HTML: https://mlsanity.com/paper/2402.13492/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 49 references that are in the map.
- First posted on arXiv 21 Feb 2024.

## Builds on (most cited first, 30 of 32)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [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)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [Making Retrieval-Augmented Language Models Robust to Irrelevant Context](https://mlsanity.com/paper/2310.01558/) (2023)
- [Generate rather than Retrieve: Large Language Models are Strong Context Generators](https://mlsanity.com/paper/2209.10063/) (2022)
- [Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models](https://mlsanity.com/paper/2311.09210/) (2023)
- [How Context Affects Language Models' Factual Predictions](https://mlsanity.com/paper/2005.04611/) (2020)
- [Large Language Models with Controllable Working Memory](https://mlsanity.com/paper/2211.05110/) (2022)
- [Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?](https://mlsanity.com/paper/2308.10168/) (2023)
- [Synthetic QA Corpora Generation with Roundtrip Consistency](https://mlsanity.com/paper/1906.05416/) (2019)
- [Simple Entity-Centric Questions Challenge Dense Retrievers](https://mlsanity.com/paper/2109.08535/) (2021)
- [RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction](https://mlsanity.com/paper/2203.09101/) (2022)

## Built on by (most cited first, 19 of 19)

- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents](https://mlsanity.com/paper/2504.09795/) (2025)
- [Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge](https://mlsanity.com/paper/2403.01432/) (2024)
- [MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge](https://mlsanity.com/paper/2412.17032/) (2024)
- [SMARTCAL: An Approach to Self-Aware Tool-Use Evaluation and Calibration](https://mlsanity.com/paper/2412.12151/) (2024)
- [Retrieval-Enhanced Machine Learning: Synthesis and Opportunities](https://mlsanity.com/paper/2407.12982/) (2024)
- [Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data](https://mlsanity.com/paper/2410.11996/) (2024)
- [What Matters in Memorizing and Recalling Facts? Multifaceted Benchmarks for Knowledge Probing in Language Models](https://mlsanity.com/paper/2406.12277/) (2024)
- [Assessing "Implicit" Retrieval Robustness of Large Language Models](https://mlsanity.com/paper/2406.18134/) (2024)
- [Orchestrating Agents and Data for Enterprise: A Blueprint Architecture for Compound AI](https://mlsanity.com/paper/2504.08148/) (2025)
- [Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG](https://mlsanity.com/paper/2511.09980/) (2025)
- [Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implications](https://mlsanity.com/paper/2602.16201/) (2026)
- [Exposing Citation Vulnerabilities in Generative Engines](https://mlsanity.com/paper/2510.06823/) (2025)
- [From Facts to Folklore: Evaluating Large Language Models on Bengali Cultural Knowledge](https://mlsanity.com/paper/2510.20043/) (2025)
- [Align Then Adapt: Label-Efficient Adapter Learning for Asymmetric Dense Retrieval](https://mlsanity.com/paper/2604.03403/) (2026)
- [CalVerT: Augmenting Agents with Calibrated Verifier Telemetry Improves Action and Learning in Knowledge-Intensive Tasks](https://mlsanity.com/paper/2606.21777/) (2026)
- [Return or Revise? Learning When Revision Helps Retrieval-Augmented QA](https://mlsanity.com/paper/2609.30087/) (2026)
- [The Chronicles of RiDiC: Generating Datasets with Controlled Popularity Distribution for Long-form Factuality Evaluation](https://mlsanity.com/paper/2604.00019/) (2026)
- [Revisiting Non-Verbatim Memorization in Large Language Models: The Role of Entity Surface Forms](https://mlsanity.com/paper/2604.21882/) (2026)

## Abstract (arXiv)

While large language models (LMs) demonstrate remarkable performance, they encounter challenges in providing accurate responses when queried for information beyond their pre-trained memorization. Although augmenting them with relevant external information can mitigate these issues, failure to consider the necessity of retrieval may adversely affect overall performance. Previous research has primarily focused on examining how entities influence retrieval models and knowledge recall in LMs, leaving other aspects relatively unexplored. In this work, our goal is to offer a more detailed, fact-centric analysis by exploring the effects of combinations of entities and relations. To facilitate this, we construct a new question answering (QA) dataset called WiTQA (Wikipedia Triple Question Answers). This dataset includes questions about entities and relations of various popularity levels, each accompanied by a supporting passage. Our extensive experiments with diverse LMs and retrievers reveal when retrieval does not consistently enhance LMs from the viewpoints of fact-centric popularity. Confirming earlier findings, we observe that larger LMs excel in recalling popular facts. However, they notably encounter difficulty with infrequent entity-relation pairs compared to retrievers. Interestingly, they can effectively retain popular relations of less common entities. We demonstrate the efficacy of our finer-grained metric and insights through an adaptive retrieval system that selectively employs retrieval and recall based on the frequencies of entities and relations in the question.