# An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks

arXiv: https://arxiv.org/abs/2210.16773 · HTML: https://mlsanity.com/paper/2210.16773/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation.
- Builds on 35 of its 43 references that are in the map.
- First posted on arXiv 30 Oct 2022.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)

## Builds on (most cited first, 30 of 35)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [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)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [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)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them](https://mlsanity.com/paper/2102.07033/) (2021)
- [A Convolutional Neural Network for Modelling Sentences](https://mlsanity.com/paper/1404.2188/) (2014)
- [End-to-End Open-Domain Question Answering with BERTserini](https://mlsanity.com/paper/1902.01718/) (2019)
- [Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets](https://mlsanity.com/paper/2008.02637/) (2020)
- [Large Memory Layers with Product Keys](https://mlsanity.com/paper/1907.05242/) (2019)
- [Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering](https://mlsanity.com/paper/1908.08167/) (2019)
- [Learning Dense Representations of Phrases at Scale](https://mlsanity.com/paper/2012.12624/) (2020)
- [A Discrete Hard EM Approach for Weakly Supervised Question Answering](https://mlsanity.com/paper/1909.04849/) (2019)
- [Augmenting Transformers with KNN-Based Composite Memory for Dialogue](https://mlsanity.com/paper/2004.12744/) (2020)
- [NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned](https://mlsanity.com/paper/2101.00133/) (2021)
- [Hindsight: Posterior-guided training of retrievers for improved open-ended generation](https://mlsanity.com/paper/2110.07752/) (2021)

## Built on by (most cited first, 30 of 36)

- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory](https://mlsanity.com/paper/2306.03901/) (2023)
- [NetLLM: Adapting Large Language Models for Networking](https://mlsanity.com/paper/2402.02338/) (2024)
- [Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering](https://mlsanity.com/paper/2410.15999/) (2024)
- [DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)](https://mlsanity.com/paper/2401.08392/) (2024)
- [KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model](https://mlsanity.com/paper/2506.20923/) (2025)
- [Creating Trustworthy LLMs: Dealing with Hallucinations in Healthcare AI](https://mlsanity.com/paper/2311.01463/) (2023)
- [ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order Optimization](https://mlsanity.com/paper/2312.15184/) (2023)
- [Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator](https://mlsanity.com/paper/2305.15099/) (2023)
- [Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute](https://mlsanity.com/paper/2301.10448/) (2023)
- [Analysing the Residual Stream of Language Models Under Knowledge Conflicts](https://mlsanity.com/paper/2410.16090/) (2024)
- [Episodic Memories Generation and Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2501.13121/) (2025)
- [The Effect of Scaling, Retrieval Augmentation and Form on the Factual Consistency of Language Models](https://mlsanity.com/paper/2311.01307/) (2023)
- [Retrieval-Enhanced Machine Learning: Synthesis and Opportunities](https://mlsanity.com/paper/2407.12982/) (2024)
- [A Comprehensive Analysis of Large Language Model Outputs: Similarity, Diversity, and Bias](https://mlsanity.com/paper/2505.09056/) (2025)
- [Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Enhanced Model Architectures](https://mlsanity.com/paper/2508.10824/) (2025)
- [GLIMMER: generalized late-interaction memory reranker](https://mlsanity.com/paper/2306.10231/) (2023)
- [Neuro Symbolic Reasoning for Planning: Counterexample Guided Inductive Synthesis using Large Language Models and Satisfiability Solving](https://mlsanity.com/paper/2309.16436/) (2023)
- [Insights into Classifying and Mitigating LLMs' Hallucinations](https://mlsanity.com/paper/2311.08117/) (2023)
- [From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems](https://mlsanity.com/paper/2506.04565/) (2025)
- [Answering Ambiguous Questions with a Database of Questions, Answers, and Revisions](https://mlsanity.com/paper/2308.08661/) (2023)
- [A Multimodal In-Context Tuning Approach for E-Commerce Product Description Generation](https://mlsanity.com/paper/2402.13587/) (2024)
- [KS-LLM: Knowledge Selection of Large Language Models with Evidence Document for Question Answering](https://mlsanity.com/paper/2404.15660/) (2024)
- [Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios](https://mlsanity.com/paper/2411.13754/) (2024)
- [AWESOME: GPU Memory-constrained Long Document Summarization using Memory Mechanism and Global Salient Content](https://mlsanity.com/paper/2305.14806/) (2023)
- [MEMORY-VQ: Compression for Tractable Internet-Scale Memory](https://mlsanity.com/paper/2308.14903/) (2023)
- [MATTER: Memory-Augmented Transformer Using Heterogeneous Knowledge Sources](https://mlsanity.com/paper/2406.04670/) (2024)
- [TTM-RE: Memory-Augmented Document-Level Relation Extraction](https://mlsanity.com/paper/2406.05906/) (2024)
- [Novel-WD: Exploring acquisition of Novel World Knowledge in LLMs Using Prefix-Tuning](https://mlsanity.com/paper/2408.17070/) (2024)
- [R4: Retrieval-Augmented Reasoning for Vision-Language Models in 4D Spatio-Temporal Space](https://mlsanity.com/paper/2512.15940/) (2025)

## Abstract (arXiv)

Access to external knowledge is essential for many natural language processing tasks, such as question answering and dialogue. Existing methods often rely on a parametric model that stores knowledge in its parameters, or use a retrieval-augmented model that has access to an external knowledge source. Parametric and retrieval-augmented models have complementary strengths in terms of computational efficiency and predictive accuracy. To combine the strength of both approaches, we propose the Efficient Memory-Augmented Transformer (EMAT) -- it encodes external knowledge into a key-value memory and exploits the fast maximum inner product search for memory querying. We also introduce pre-training tasks that allow EMAT to encode informative key-value representations, and to learn an implicit strategy to integrate multiple memory slots into the transformer. Experiments on various knowledge-intensive tasks such as question answering and dialogue datasets show that, simply augmenting parametric models (T5-base) using our method produces more accurate results (e.g., 25.8 -> 44.3 EM on NQ) while retaining a high throughput (e.g., 1000 queries/s on NQ). Compared to retrieval-augmented models, EMAT runs substantially faster across the board and produces more accurate results on WoW and ELI5. Our code and datasets are available at https://github. com/uclnlp/EMAT.