# DynamicRetriever: A Pre-training Model-based IR System with Neither Sparse nor Dense Index

arXiv: https://arxiv.org/abs/2203.00537 · HTML: https://mlsanity.com/paper/2203.00537/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2022.

## Built on by (most cited first, 12 of 12)

- [CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Tasks](https://mlsanity.com/paper/2208.07652/) (2022)
- [Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration](https://mlsanity.com/paper/2405.16546/) (2024)
- [A Survey of Generative Search and Recommendation in the Era of Large Language Models](https://mlsanity.com/paper/2404.16924/) (2024)
- [UniGen: A Unified Generative Framework for Retrieval and Question Answering with Large Language Models](https://mlsanity.com/paper/2312.11036/) (2023)
- [Evaluating Generative Ad Hoc Information Retrieval](https://mlsanity.com/paper/2311.04694/) (2023)
- [Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval](https://mlsanity.com/paper/2504.05181/) (2025)
- [Asking Multimodal Clarifying Questions in Mixed-Initiative Conversational Search](https://mlsanity.com/paper/2402.07742/) (2024)
- [Exploring the Practicality of Generative Retrieval on Dynamic Corpora](https://mlsanity.com/paper/2305.18952/) (2023)
- [Self-Retrieval: End-to-End Information Retrieval with One Large Language Model](https://mlsanity.com/paper/2403.00801/) (2024)
- [A Survey of Generative Information Retrieval](https://mlsanity.com/paper/2406.01197/) (2024)
- [DiffuGR: Generative Document Retrieval with Diffusion Language Models](https://mlsanity.com/paper/2511.08150/) (2025)
- [Uncertainty-driven Embedding Convolution](https://mlsanity.com/paper/2507.20718/) (2025)

## Abstract (arXiv)

Web search provides a promising way for people to obtain information and has been extensively studied. With the surgence of deep learning and large-scale pre-training techniques, various neural information retrieval models are proposed and they have demonstrated the power for improving search (especially, the ranking) quality. All these existing search methods follow a common paradigm, i.e. index-retrieve-rerank, where they first build an index of all documents based on document terms (i.e., sparse inverted index) or representation vectors (i.e., dense vector index), then retrieve and rerank retrieved documents based on similarity between the query and documents via ranking models. In this paper, we explore a new paradigm of information retrieval with neither sparse nor dense index but only a model. Specifically, we propose a pre-training model-based IR system called DynamicRetriever. As for this system, the training stage embeds the token-level and document-level information (especially, document identifiers) of the corpus into the model parameters, then the inference stage directly generates document identifiers for a given query. Compared with existing search methods, the model-based IR system has two advantages: i) it parameterizes the traditional static index with a pre-training model, which converts the document semantic mapping into a dynamic and updatable process; ii) with separate document identifiers, it captures both the term-level and document-level information for each document. Extensive experiments conducted on the public search benchmark MS MARCO verify the effectiveness and potential of our proposed new paradigm for information retrieval.