mlsanityData to 7 Oct 2026

CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning

arXiv 2112.08558 ↗First posted 16 Dec 2021cs.CLcited by 68

Not on the map. Why?

Abstract (arXiv)

Compared to standard retrieval tasks, passage retrieval for conversational question answering (CQA) poses new challenges in understanding the current user question, as each question needs to be interpreted within the dialogue context. Moreover, it can be expensive to re-train well-established retrievers such as search engines that are originally developed for non-conversational queries. To facilitate their use, we develop a query rewriting model CONQRR that rewrites a conversational question in the context into a standalone question. It is trained with a novel reward function to directly optimize towards retrieval using reinforcement learning and can be adapted to any off-the-shelf retriever. CONQRR achieves state-of-the-art results on a recent open-domain CQA dataset containing conversations from three different sources, and is effective for two different off-the-shelf retrievers. Our extensive analysis also shows the robustness of CONQRR to out-of-domain dialogues as well as to zero query rewriting supervision.

Key facts. Cited by 68 papers in the map (data through 7 Oct 2026). Builds on 31 of its 52 references that are in the map. First posted on arXiv 16 Dec 2021.

Builds on

31 of 52 references.

References · 31

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  4. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  5. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
  6. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 896
  7. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  8. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  9. 2018CoQA: A Conversational Question Answering Challengecited by 674
  10. 2015Sequence Level Training with Recurrent Neural Networkscited by 568
  11. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 462
  12. 2021Large Dual Encoders Are Generalizable Retrieverscited by 454
19 more
  1. 2018QuAC : Question Answering in Contextcited by 379
  2. 2017A Deep Reinforced Model for Abstractive Summarizationcited by 364
  3. 2021Internet-Augmented Dialogue Generationcited by 217
  4. 2020Sparse, Dense, and Attentional Representations for Text Retrievalcited by 213
  5. 2020Open-Domain Question Answering Goes Conversational via Question Rewritingcited by 147
  6. 2021Decontextualization: Making Sentences Stand-Alonecited by 101
  7. 2020Open-Retrieval Conversational Question Answeringcited by 99
  8. 2020Question Rewriting for Conversational Question Answeringcited by 93
  9. 2020Few-Shot Generative Conversational Query Rewritingcited by 85
  10. 2020Query Resolution for Conversational Search with Limited Supervisioncited by 52
  11. 2018Deep Communicating Agents for Abstractive Summarizationcited by 50
  12. 2020Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Modelscited by 45
  13. 2017Ask the Right Questions: Active Question Reformulation with Reinforcement Learningcited by 44
  14. 2017Task-Oriented Query Reformulation with Reinforcement Learningcited by 39
  15. 2021Contextualized Query Embeddings for Conversational Searchcited by 36
  16. 2021Boosting Search Engines with Interactive Agentscited by 19
  17. 2019Context Attentive Document Ranking and Query Suggestioncited by 15
  18. 2018Attention-based Hierarchical Neural Query Suggestioncited by 5
  19. 2021Automatic Document Sketching: Generating Drafts from Analogous Textscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 12; 2024: 21; 2025: 15; 2026: 12.

68 papers.

Sort:

By area:

  1. 2023Augmented Language Models: a Surveycited by 398
  2. 2024ChatQA: Surpassing GPT-4 on Conversational QA and RAGcited by 90
  3. 2023Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewritingcited by 69
  4. 2024Bridging the Preference Gap between Retrievers and LLMscited by 69
  5. 2023ConvGQR: Generative Query Reformulation for Conversational Searchcited by 59
  6. 2022Dialog Inpainting: Turning Documents into Dialogscited by 56
  7. 2024RaFe: Ranking Feedback Improves Query Rewriting for RAGcited by 47
  8. 2023Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinementcited by 43
  9. 2024CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Searchcited by 29
  10. 2023Learning to Relate to Previous Turns in Conversational Searchcited by 26
  11. 2024Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversationcited by 23
  12. 2024A Survey of Conversational Searchcited by 22
38 more
  1. 2022Reinforced Question Rewriting for Conversational Question Answeringcited by 19
  2. 2024Conv-CoA: Improving Open-domain Question Answering in Large Language Models via Conversational Chain-of-Actioncited by 19
  3. 2022Saving Dense Retriever from Shortcut Dependency in Conversational Searchcited by 18
  4. 2024ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrievalcited by 18
  5. 2023Query Performance Prediction: From Ad-hoc to Conversational Searchcited by 16
  6. 2024Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentationcited by 16
  7. 2024AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignmentcited by 14
  8. 2025UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversationscited by 11
  9. 2022Q-TOD: A Query-driven Task-oriented Dialogue Systemcited by 10
  10. 2024How to Leverage Personal Textual Knowledge for Personalized Conversational Information Retrievalcited by 10
  11. 2024Aligning Query Representation with Rewritten Query and Relevance Judgments in Conversational Searchcited by 10
  12. 2025Wizard of Shopping: Target-Oriented E-commerce Dialogue Generation with Decision Tree Branchingcited by 10
  13. 2023Human-centered NLP Fact-checking: Co-Designing with Fact-checkers using Matchmaking for AIcited by 9
  14. 2024Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QAcited by 9
  15. 2024No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Userscited by 9
  16. 2024ConvSDG: Session Data Generation for Conversational Searchcited by 8
  17. 2024DiSCo: LLM Knowledge Distillation for Efficient Sparse Retrieval in Conversational Searchcited by 8
  18. 2024CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generationcited by 8
  19. 2025Conversational Search: From Fundamentals to Frontiers in the LLM Eracited by 8
  20. 2023Query Understanding in the Age of Large Language Modelscited by 7
  21. 2025RECAP: REwriting Conversations for Intent Understanding in Agentic Planningcited by 7
  22. 2023CONVERSER: Few-Shot Conversational Dense Retrieval with Synthetic Data Generationcited by 6
  23. 2022Decoding a Neural Retriever's Latent Space for Query Suggestioncited by 5
  24. 2024History-Aware Conversational Dense Retrievalcited by 4
  25. 2025ConvMix: A Mixed-Criteria Data Augmentation Framework for Conversational Dense Retrievalcited by 4
  26. 2025ICR: Iterative Clarification and Rewriting for Conversational Searchcited by 4
  27. 2024UniRetriever: Multi-task Candidates Selection for Various Context-Adaptive Conversational Retrievalcited by 3
  28. 2022Query Rewriting for Effective Misinformation Discoverycited by 2
  29. 2022Query Enhanced Knowledge-Intensive Conversation via Unsupervised Joint Modelingcited by 2
  30. 2023Phrase Retrieval for Open-Domain Conversational Question Answering with Conversational Dependency Modeling via Contrastive Learningcited by 2
  31. 2024Synthesizing Conversations from Unlabeled Documents using Automatic Response Segmentationcited by 2
  32. 2024Conversational Query Reformulation with the Guidance of Retrieved Documentscited by 2
  33. 2025AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptationcited by 2
  34. 2022Dense Paraphrasing for Textual Enrichmentcited by 1
  35. 2025Exploring Rewriting Approaches for Different Conversational Taskscited by 1
  36. 2025QUPID: Quantified Understanding for Enhanced Performance, Insights, and Decisions in Korean Search Enginescited by 1
  37. 2025Read the Docs Before Rewriting: Equip Rewriter with Domain Knowledge via Continual Pre-trainingcited by 1
  38. 2025Test-Time Scaling Strategies for Generative Retrieval in Multimodal Conversational Recommendationscited by 1

50 most cited of 68 All 68 (JSON)