mlsanityData to 7 Oct 2026

Few-Shot Generative Conversational Query Rewriting

arXiv 2006.05009 ↗First posted 9 Jun 2020cs.IRcited by 85

Not on the map. Why?

Abstract (arXiv)

Conversational query rewriting aims to reformulate a concise conversational query to a fully specified, context-independent query that can be effectively handled by existing information retrieval systems. This paper presents a few-shot generative approach to conversational query rewriting. We develop two methods, based on rules and self-supervised learning, to generate weak supervision data using large amounts of ad hoc search sessions, and to fine-tune GPT-2 to rewrite conversational queries. On the TREC Conversational Assistance Track, our weakly supervised GPT-2 rewriter improves the state-of-the-art ranking accuracy by 12%, only using very limited amounts of manual query rewrites. In the zero-shot learning setting, the rewriter still gives a comparable result to previous state-of-the-art systems. Our analyses reveal that GPT-2 effectively picks up the task syntax and learns to capture context dependencies, even for hard cases that involve group references and long-turn dependencies.

Key facts. Cited by 85 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 9; 2023: 23; 2024: 23; 2025: 12; 2026: 8.

85 papers.

Sort:

By area:

  1. 2024ChatQA: Surpassing GPT-4 on Conversational QA and RAGcited by 90
  2. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Modelscited by 77
  3. 2023Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewritingcited by 69
  4. 2021CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learningcited by 68
  5. 2023ConvGQR: Generative Query Reformulation for Conversational Searchcited by 59
  6. 2024CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Modelscited by 50
  7. 2024Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrievalcited by 50
  8. 2023Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinementcited by 43
  9. 2022Neural Approaches to Conversational Information Retrievalcited by 41
  10. 2024CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Searchcited by 29
  11. 2021MS MARCO: Benchmarking Ranking Models in the Large-Data Regimecited by 28
  12. 2023Learning to Relate to Previous Turns in Conversational Searchcited by 26
38 more
  1. 2024Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversationcited by 23
  2. 2024A Survey of Conversational Searchcited by 22
  3. 2021Reinforcement Learning from Reformulations in Conversational Question Answering over Knowledge Graphscited by 18
  4. 2022Saving Dense Retriever from Shortcut Dependency in Conversational Searchcited by 18
  5. 2024ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrievalcited by 18
  6. 2021A Comparison of Question Rewriting Methods for Conversational Passage Retrievalcited by 16
  7. 2023Query Performance Prediction: From Ad-hoc to Conversational Searchcited by 16
  8. 2023Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answeringcited by 15
  9. 2024Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answerscited by 15
  10. 2023Zero-shot Clarifying Question Generation for Conversational Searchcited by 14
  11. 2024AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignmentcited by 14
  12. 2021Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQLcited by 13
  13. 2021What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Datacited by 10
  14. 2024How to Leverage Personal Textual Knowledge for Personalized Conversational Information Retrievalcited by 10
  15. 2024Aligning Query Representation with Rewritten Query and Relevance Judgments in Conversational Searchcited by 10
  16. 2025Wizard of Shopping: Target-Oriented E-commerce Dialogue Generation with Decision Tree Branchingcited by 10
  17. 2025ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidancecited by 10
  18. 2023Talk the Walk: Synthetic Data Generation for Conversational Music Recommendationcited by 9
  19. 2023Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understandingcited by 8
  20. 2024ConvSDG: Session Data Generation for Conversational Searchcited by 8
  21. 2024CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generationcited by 8
  22. 2025Conversational Search: From Fundamentals to Frontiers in the LLM Eracited by 8
  23. 2023Query Understanding in the Age of Large Language Modelscited by 7
  24. 2023Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generationcited by 7
  25. 2022McQueen: a Benchmark for Multimodal Conversational Query Rewritecited by 6
  26. 2023Beyond Single Items: Exploring User Preferences in Item Sets with the Conversational Playlist Curation Datasetcited by 6
  27. 2023Generate-then-Retrieve: Intent-Aware FAQ Retrieval in Product Searchcited by 6
  28. 2024CoSearchAgent: A Lightweight Collaborative Search Agent with Large Language Modelscited by 6
  29. 2021Conversational Query Rewriting with Self-supervised Learningcited by 5
  30. 2022From Rewriting to Remembering: Common Ground for Conversational QA Modelscited by 5
  31. 2022SCAI-QReCC Shared Task on Conversational Question Answeringcited by 4
  32. 2023ZeQR: Zero-shot Query Reformulation for Conversational Searchcited by 4
  33. 2023Learning to Select the Relevant History Turns in Conversational Question Answeringcited by 4
  34. 2024History-Aware Conversational Dense Retrievalcited by 4
  35. 2025Query Understanding in LLM-based Conversational Information Seekingcited by 4
  36. 2025ConvMix: A Mixed-Criteria Data Augmentation Framework for Conversational Dense Retrievalcited by 4
  37. 2021High-Quality Diversification for Task-Oriented Dialogue Systemscited by 3
  38. 2023Keeping the Questions Conversational: Using Structured Representations to Resolve Dependency in Conversational Question Answeringcited by 3

50 most cited of 85 All 85 (JSON)