# Document Expansion by Query Prediction

arXiv: https://arxiv.org/abs/1904.08375 · HTML: https://mlsanity.com/paper/1904.08375/

## Key facts

- Cited by 231 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2019.

## Built on by (most cited first, 30 of 231)

- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023)
- [Improving Text Embeddings with Large Language Models](https://mlsanity.com/paper/2401.00368/) (2023)
- [Transformer Memory as a Differentiable Search Index](https://mlsanity.com/paper/2202.06991/) (2022)
- [PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them](https://mlsanity.com/paper/2102.07033/) (2021)
- [Overview of the TREC 2020 deep learning track](https://mlsanity.com/paper/2102.07662/) (2021)
- [RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking](https://mlsanity.com/paper/2110.07367/) (2021)
- [Query2doc: Query Expansion with Large Language Models](https://mlsanity.com/paper/2303.07678/) (2023)
- [AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web](https://mlsanity.com/paper/2305.13117/) (2023)
- [SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval](https://mlsanity.com/paper/2109.10086/) (2021)
- [GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval](https://mlsanity.com/paper/2112.07577/) (2021)
- [Autoregressive Search Engines: Generating Substrings as Document Identifiers](https://mlsanity.com/paper/2204.10628/) (2022)
- [Task-aware Retrieval with Instructions](https://mlsanity.com/paper/2211.09260/) (2022)
- [Gemini Embedding: Generalizable Embeddings from Gemini](https://mlsanity.com/paper/2503.07891/) (2025)
- [Adversarial Retriever-Ranker for dense text retrieval](https://mlsanity.com/paper/2110.03611/) (2021)
- [The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models](https://mlsanity.com/paper/2101.05667/) (2021)
- [Rank1: Test-Time Compute for Reranking in Information Retrieval](https://mlsanity.com/paper/2502.18418/) (2025)
- [Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrieval](https://mlsanity.com/paper/2408.01875/) (2024)
- [PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval](https://mlsanity.com/paper/2108.06027/) (2021)
- [How Does Generative Retrieval Scale to Millions of Passages?](https://mlsanity.com/paper/2305.11841/) (2023)
- [MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories](https://mlsanity.com/paper/2104.13615/) (2021)
- [ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval](https://mlsanity.com/paper/2205.09153/) (2022)
- [GERE: Generative Evidence Retrieval for Fact Verification](https://mlsanity.com/paper/2204.05511/) (2022)
- [Towards Robust Ranker for Text Retrieval](https://mlsanity.com/paper/2206.08063/) (2022)
- [Scaling Laws For Dense Retrieval](https://mlsanity.com/paper/2403.18684/) (2024)
- [What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary](https://mlsanity.com/paper/2212.10380/) (2022)
- [Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval](https://mlsanity.com/paper/2203.03367/) (2022)
- [An Efficiency Study for SPLADE Models](https://mlsanity.com/paper/2207.03834/) (2022)
- [When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasets](https://mlsanity.com/paper/2309.08541/) (2023)
- [Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.00306/) (2025)

## Abstract (arXiv)

One technique to improve the retrieval effectiveness of a search engine is to expand documents with terms that are related or representative of the documents' content.From the perspective of a question answering system, this might comprise questions the document can potentially answer. Following this observation, we propose a simple method that predicts which queries will be issued for a given document and then expands it with those predictions with a vanilla sequence-to-sequence model, trained using datasets consisting of pairs of query and relevant documents. By combining our method with a highly-effective re-ranking component, we achieve the state of the art in two retrieval tasks. In a latency-critical regime, retrieval results alone (without re-ranking) approach the effectiveness of more computationally expensive neural re-rankers but are much faster.