# TOME: A Two-stage Approach for Model-based Retrieval

arXiv: https://arxiv.org/abs/2305.11161 · HTML: https://mlsanity.com/paper/2305.11161/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 May 2023.

## Built on by (most cited first, 21 of 21)

- [Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation](https://mlsanity.com/paper/2307.11019/) (2023)
- [Learning to Rank in Generative Retrieval](https://mlsanity.com/paper/2306.15222/) (2023)
- [BASES: Large-scale Web Search User Simulation with Large Language Model based Agents](https://mlsanity.com/paper/2402.17505/) (2024)
- [Planning Ahead in Generative Retrieval: Guiding Autoregressive Generation through Simultaneous Decoding](https://mlsanity.com/paper/2404.14600/) (2024)
- [GLEN: Generative Retrieval via Lexical Index Learning](https://mlsanity.com/paper/2311.03057/) (2023)
- [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)
- [Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval](https://mlsanity.com/paper/2504.05181/) (2025)
- [Beyond Memorization: The Challenge of Random Memory Access in Language Models](https://mlsanity.com/paper/2403.07805/) (2024)
- [Revolutionizing Text-to-Image Retrieval as Autoregressive Token-to-Voken Generation](https://mlsanity.com/paper/2407.17274/) (2024)
- [CoRank: LLM-Based Compact Reranking with Document Features for Scientific Retrieval](https://mlsanity.com/paper/2505.13757/) (2025)
- [A Survey of Generative Information Retrieval](https://mlsanity.com/paper/2406.01197/) (2024)
- [Exploring Training and Inference Scaling Laws in Generative Retrieval](https://mlsanity.com/paper/2503.18941/) (2025)
- [Generative Retrieval with Few-shot Indexing](https://mlsanity.com/paper/2408.02152/) (2024)
- [T2VIndexer: A Generative Video Indexer for Efficient Text-Video Retrieval](https://mlsanity.com/paper/2408.11432/) (2024)
- [MAC-Tuning: LLM Multi-Compositional Problem Reasoning with Enhanced Knowledge Boundary Awareness](https://mlsanity.com/paper/2504.21773/) (2025)
- [Bootstrapped Pre-training with Dynamic Identifier Prediction for Generative Retrieval](https://mlsanity.com/paper/2407.11504/) (2024)
- [Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models](https://mlsanity.com/paper/2506.17585/) (2025)
- [MindRef: Mimicking Human Memory for Hierarchical Reference Retrieval with Fine-Grained Location Awareness](https://mlsanity.com/paper/2402.17010/) (2024)
- [From Relevance to Authority: Authority-aware Generative Retrieval in Web Search Engines](https://mlsanity.com/paper/2604.13468/) (2026)
- [A Parametric Memory Head for Continual Generative Retrieval](https://mlsanity.com/paper/2604.23388/) (2026)

## Abstract (arXiv)

Recently, model-based retrieval has emerged as a new paradigm in text retrieval that discards the index in the traditional retrieval model and instead memorizes the candidate corpora using model parameters. This design employs a sequence-to-sequence paradigm to generate document identifiers, which enables the complete capture of the relevance between queries and documents and simplifies the classic indexretrieval-rerank pipeline. Despite its attractive qualities, there remain several major challenges in model-based retrieval, including the discrepancy between pre-training and fine-tuning, and the discrepancy between training and inference. To deal with the above challenges, we propose a novel two-stage model-based retrieval approach called TOME, which makes two major technical contributions, including the utilization of tokenized URLs as identifiers and the design of a two-stage generation architecture. We also propose a number of training strategies to deal with the training difficulty as the corpus size increases. Extensive experiments and analysis on MS MARCO and Natural Questions demonstrate the effectiveness of our proposed approach, and we investigate the scaling laws of TOME by examining various influencing factors.