# Autoregressive Search Engines: Generating Substrings as Document Identifiers

arXiv: https://arxiv.org/abs/2204.10628 · HTML: https://mlsanity.com/paper/2204.10628/

## Key facts

- Cited by 113 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 77 references that are in the map.
- First posted on arXiv 22 Apr 2022.

## Builds on (most cited first, 30 of 55)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [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)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [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)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model](https://mlsanity.com/paper/2201.11990/) (2022)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [Zero-Shot Relation Extraction via Reading Comprehension](https://mlsanity.com/paper/1706.04115/) (2017)
- [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [Transformer Memory as a Differentiable Search Index](https://mlsanity.com/paper/2202.06991/) (2022)
- [Document Expansion by Query Prediction](https://mlsanity.com/paper/1904.08375/) (2019)
- [Internet-Augmented Dialogue Generation](https://mlsanity.com/paper/2107.07566/) (2021)
- [PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them](https://mlsanity.com/paper/2102.07033/) (2021)
- [Generation-Augmented Retrieval for Open-domain Question Answering](https://mlsanity.com/paper/2009.08553/) (2020)
- [How Context Affects Language Models' Factual Predictions](https://mlsanity.com/paper/2005.04611/) (2020)
- [Efficient Large Scale Language Modeling with Mixtures of Experts](https://mlsanity.com/paper/2112.10684/) (2021)

## Built on by (most cited first, 30 of 113)

- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [LeanDojo: Theorem Proving with Retrieval-Augmented Language Models](https://mlsanity.com/paper/2306.15626/) (2023)
- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [Generate rather than Retrieve: Large Language Models are Strong Context Generators](https://mlsanity.com/paper/2209.10063/) (2022)
- [Re2G: Retrieve, Rerank, Generate](https://mlsanity.com/paper/2207.06300/) (2022)
- [From Matching to Generation: A Survey on Generative Information Retrieval](https://mlsanity.com/paper/2404.14851/) (2024)
- [A Survey on Retrieval-Augmented Text Generation for Large Language Models](https://mlsanity.com/paper/2404.10981/) (2024)
- [VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval](https://mlsanity.com/paper/2406.04292/) (2024)
- [Recitation-Augmented Language Models](https://mlsanity.com/paper/2210.01296/) (2022)
- [FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2209.14290/) (2022)
- [Chain-of-Retrieval Augmented Generation](https://mlsanity.com/paper/2501.14342/) (2025)
- [Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation](https://mlsanity.com/paper/2206.10128/) (2022)
- [How Does Generative Retrieval Scale to Millions of Passages?](https://mlsanity.com/paper/2305.11841/) (2023)
- [Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models](https://mlsanity.com/paper/2305.09955/) (2023)
- [Learning to Rank in Generative Retrieval](https://mlsanity.com/paper/2306.15222/) (2023)
- [CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Tasks](https://mlsanity.com/paper/2208.07652/) (2022)
- [PEDANTS: Cheap but Effective and Interpretable Answer Equivalence](https://mlsanity.com/paper/2402.11161/) (2024)
- [Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization](https://mlsanity.com/paper/2405.02816/) (2024)
- [What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary](https://mlsanity.com/paper/2212.10380/) (2022)
- [Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications](https://mlsanity.com/paper/2311.05876/) (2023)
- [Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond](https://mlsanity.com/paper/2402.10805/) (2024)
- [Large Language Models are Built-in Autoregressive Search Engines](https://mlsanity.com/paper/2305.09612/) (2023)
- [ALR2: A Retrieve-then-Reason Framework for Long-context Question Answering](https://mlsanity.com/paper/2410.03227/) (2024)
- [Evaluating n-Gram Novelty of Language Models Using Rusty-DAWG](https://mlsanity.com/paper/2406.13069/) (2024)
- [RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation](https://mlsanity.com/paper/2412.11919/) (2024)
- [Planning Ahead in Generative Retrieval: Guiding Autoregressive Generation through Simultaneous Decoding](https://mlsanity.com/paper/2404.14600/) (2024)
- [IRGen: Generative Modeling for Image Retrieval](https://mlsanity.com/paper/2303.10126/) (2023)
- [CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks](https://mlsanity.com/paper/2402.01176/) (2024)
- [Unifying Generative and Dense Retrieval for Sequential Recommendation](https://mlsanity.com/paper/2411.18814/) (2024)

## Abstract (arXiv)

Knowledge-intensive language tasks require NLP systems to both provide the correct answer and retrieve supporting evidence for it in a given corpus. Autoregressive language models are emerging as the de-facto standard for generating answers, with newer and more powerful systems emerging at an astonishing pace. In this paper we argue that all this (and future) progress can be directly applied to the retrieval problem with minimal intervention to the models' architecture. Previous work has explored ways to partition the search space into hierarchical structures and retrieve documents by autoregressively generating their unique identifier. In this work we propose an alternative that doesn't force any structure in the search space: using all ngrams in a passage as its possible identifiers. This setup allows us to use an autoregressive model to generate and score distinctive ngrams, that are then mapped to full passages through an efficient data structure. Empirically, we show this not only outperforms prior autoregressive approaches but also leads to an average improvement of at least 10 points over more established retrieval solutions for passage-level retrieval on the KILT benchmark, establishing new state-of-the-art downstream performance on some datasets, while using a considerably lighter memory footprint than competing systems. Code and pre-trained models at https://github.com/facebookresearch/SEAL.