mlsanityData to 14 Oct 2026

QueStER: Query Specification for Generative keyword-based Retrieval

arXiv 2511.05301 ↗First posted 7 Nov 2025cs.IR cs.CL cs.LGcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper 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

32 of 49 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  5. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  6. 2019Passage Re-ranking with BERTcited by 645
  7. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  8. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 476
  9. 2025Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Modelcited by 461
  10. 2021SPLADE v2: Sparse Lexical and Expansion Model for Information Retrievalcited by 127
  11. 2022Autoregressive Search Engines: Generating Substrings as Document Identifierscited by 113
  12. 2023Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewritingcited by 69
20 more
  1. 2023Learning to Tokenize for Generative Retrievalcited by 68
  2. 2023Large Language Model based Long-tail Query Rewriting in Taobao Searchcited by 62
  3. 2024RaFe: Ranking Feedback Improves Query Rewriting for RAGcited by 49
  4. 2023How Does Generative Retrieval Scale to Millions of Passages?cited by 48
  5. 2017Task-Oriented Query Reformulation with Reinforcement Learningcited by 39
  6. 2022GERE: Generative Evidence Retrieval for Fact Verificationcited by 38
  7. 2022CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Taskscited by 36
  8. 2022Ultron: An Ultimate Retriever on Corpus with a Model-based Indexercited by 31
  9. 2023Semantic-Enhanced Differentiable Search Index Inspired by Learning Strategiescited by 25
  10. 2023GLEN: Generative Retrieval via Lexical Index Learningcited by 17
  11. 2024Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrievalcited by 17
  12. 2023Auto Search Indexer for End-to-End Document Retrievalcited by 16
  13. 2023Generative Retrieval via Term Set Generationcited by 13
  14. 2023Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?cited by 12
  15. 2025Can Generative LLMs Create Query Variants for Test Collections? An Exploratory Studycited by 10
  16. 2023Generative and Pseudo-Relevant Feedback for Sparse, Dense and Learned Sparse Retrievalcited by 9
  17. 2025Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrievalcited by 8
  18. 2024DeeperImpact: Optimizing Sparse Learned Index Structurescited by 5
  19. 2022On Survivorship Bias in MS MARCOcited by 4
  20. 2025Rational Retrieval Acts: Leveraging Pragmatic Reasoning to Improve Sparse Retrievalcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026STORM: Stepwise Token Optimization with Reward-Guided Beam Searchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Tool-Adaptive LLM Reranker
  2. 2026It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning
  3. 2025Exploring Training and Inference Scaling Laws in Generative Retrieval
  4. 2025DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation
  5. 2025InPars+: Supercharging Synthetic Data Generation for Information Retrieval Systems
  6. 2025Rethinking On-policy Optimization for Query Augmentation
  7. 2025Annotation-Free Reinforcement Learning Query Rewriting via Verifiable Search Reward
  8. 2025From Prompting to Alignment: A Generative Framework for Query Recommendation