# QueStER: Query Specification for Generative keyword-based Retrieval

arXiv: https://arxiv.org/abs/2511.05301 · HTML: https://mlsanity.com/paper/2511.05301/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 49 references that are in the map.
- First posted on arXiv 7 Nov 2025.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://mlsanity.com/paper/2112.01488/) (2021)
- [Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model](https://mlsanity.com/paper/2503.24290/) (2025)
- [SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval](https://mlsanity.com/paper/2109.10086/) (2021)
- [Autoregressive Search Engines: Generating Substrings as Document Identifiers](https://mlsanity.com/paper/2204.10628/) (2022)
- [Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewriting](https://mlsanity.com/paper/2310.09716/) (2023)
- [Learning to Tokenize for Generative Retrieval](https://mlsanity.com/paper/2304.04171/) (2023)
- [Large Language Model based Long-tail Query Rewriting in Taobao Search](https://mlsanity.com/paper/2311.03758/) (2023)
- [RaFe: Ranking Feedback Improves Query Rewriting for RAG](https://mlsanity.com/paper/2405.14431/) (2024)
- [How Does Generative Retrieval Scale to Millions of Passages?](https://mlsanity.com/paper/2305.11841/) (2023)
- [Task-Oriented Query Reformulation with Reinforcement Learning](https://mlsanity.com/paper/1704.04572/) (2017)
- [GERE: Generative Evidence Retrieval for Fact Verification](https://mlsanity.com/paper/2204.05511/) (2022)
- [CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Tasks](https://mlsanity.com/paper/2208.07652/) (2022)
- [Ultron: An Ultimate Retriever on Corpus with a Model-based Indexer](https://mlsanity.com/paper/2208.09257/) (2022)
- [Semantic-Enhanced Differentiable Search Index Inspired by Learning Strategies](https://mlsanity.com/paper/2305.15115/) (2023)
- [GLEN: Generative Retrieval via Lexical Index Learning](https://mlsanity.com/paper/2311.03057/) (2023)
- [Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval](https://mlsanity.com/paper/2410.23214/) (2024)
- [Auto Search Indexer for End-to-End Document Retrieval](https://mlsanity.com/paper/2310.12455/) (2023)
- [Generative Retrieval via Term Set Generation](https://mlsanity.com/paper/2305.13859/) (2023)
- [Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?](https://mlsanity.com/paper/2311.09175/) (2023)
- [Can Generative LLMs Create Query Variants for Test Collections? An Exploratory Study](https://mlsanity.com/paper/2501.17981/) (2025)
- [Generative and Pseudo-Relevant Feedback for Sparse, Dense and Learned Sparse Retrieval](https://mlsanity.com/paper/2305.07477/) (2023)
- [Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval](https://mlsanity.com/paper/2506.00041/) (2025)
- [DeeperImpact: Optimizing Sparse Learned Index Structures](https://mlsanity.com/paper/2405.17093/) (2024)

## Built on by (most cited first, 1 of 1)

- [STORM: Stepwise Token Optimization with Reward-Guided Beam Search](https://mlsanity.com/paper/2606.10621/) (2026)

## Abstract (arXiv)

Generative retrieval (GR) differs from the traditional index-then-retrieve pipeline by storing relevance in model parameters and generating retrieval cues directly from the query, but it can be brittle out of domain and expensive to scale. We introduce QueStER (QUEry SpecificaTion for gEnerative Keyword-Based Retrieval), which bridges GR and query reformulation by learning to generate explicit keyword-based search specifications. Given a user query, a lightweight LLM produces a keyword query that is executed by a standard retriever (BM25), combining the generalization benefits of generative query rewriting with the efficiency and scalability of lexical indexing. We train the rewriting policy with reinforcement learning techniques. Across in- and out-of-domain evaluations, QueStER consistently improves over BM25 and is competitive with neural IR baselines, while maintaining strong efficiency.