# Generative Retrieval via Term Set Generation

arXiv: https://arxiv.org/abs/2305.13859 · HTML: https://mlsanity.com/paper/2305.13859/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2023.

## Built on by (most cited first, 13 of 13)

- [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)
- [RAMQA: A Unified Framework for Retrieval-Augmented Multi-Modal Question Answering](https://mlsanity.com/paper/2501.13297/) (2025)
- [On Synthetic Data Strategies for Domain-Specific Generative Retrieval](https://mlsanity.com/paper/2502.17957/) (2025)
- [SemCORE: A Semantic-Enhanced Generative Cross-Modal Retrieval Framework with MLLMs](https://mlsanity.com/paper/2504.13172/) (2025)
- [MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora](https://mlsanity.com/paper/2507.09924/) (2025)
- [Multilingual Generative Retrieval via Cross-lingual Semantic Compression](https://mlsanity.com/paper/2510.07812/) (2025)
- [Summarization-Based Document IDs for Generative Retrieval with Language Models](https://mlsanity.com/paper/2311.08593/) (2023)
- [PromptDSI: Prompt-based Rehearsal-free Continual Learning for Document Retrieval](https://mlsanity.com/paper/2406.12593/) (2024)
- [Retrieval-in-the-Chain: Bootstrapping Large Language Models for Generative Retrieval](https://mlsanity.com/paper/2510.13095/) (2025)
- [QueStER: Query Specification for Generative keyword-based Retrieval](https://mlsanity.com/paper/2511.05301/) (2025)
- [A Simple and Effective Framework for Symmetric Consistent Indexing in Large-Scale Dense Retrieval](https://mlsanity.com/paper/2512.13074/) (2025)
- [Generative Universal Multimodal Retrieval with Dual-role Identifiers](https://mlsanity.com/paper/2608.12987/) (2026)

## Abstract (arXiv)

Recently, generative retrieval emerges as a promising alternative to traditional retrieval paradigms. It assigns each document a unique identifier, known as DocID, and employs a generative model to directly generate the relevant DocID for the input query. A common choice for DocID is one or several natural language sequences, e.g. the title or n-grams, so that the pre-trained knowledge of the generative model can be utilized. However, a sequence is generated token by token, where only the most likely candidates are kept and the rest are pruned at each decoding step, thus, retrieval fails if any token within the relevant DocID is falsely pruned. What's worse, during decoding, the model can only perceive preceding tokens in DocID while being blind to subsequent ones, hence is prone to make such errors. To address this problem, we present a novel framework for generative retrieval, dubbed Term-Set Generation (TSGen). Instead of sequences, we use a set of terms as DocID, which are automatically selected to concisely summarize the document's semantics and distinguish it from others. On top of the term-set DocID, we propose a permutation-invariant decoding algorithm, with which the term set can be generated in any permutation yet will always lead to the corresponding document. Remarkably, TSGen perceives all valid terms rather than only the preceding ones at each decoding step. Given the constant decoding space, it can make more reliable decisions due to the broader perspective. TSGen is also resilient to errors: the relevant DocID will not be pruned as long as the decoded term belongs to it. Lastly, we design an iterative optimization procedure to incentivize the model to generate the relevant term set in its favorable permutation. We conduct extensive experiments on popular benchmarks, which validate the effectiveness, the generalizability, the scalability, and the efficiency of TSGen.