AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptation
Not on the map. Why?
Abstract (arXiv)
Prompting-based conversational query reformulation has emerged as a powerful approach for conversational search, refining ambiguous user queries into standalone search queries. Best-of-N reformulation over the generated candidates via prompting shows impressive potential scaling capability. However, both the previous tuning methods (training time) and adaptation approaches (test time) can not fully unleash their benefits. In this paper, we propose AdaRewriter, a novel framework for query reformulation using an outcome-supervised reward model via test-time adaptation. By training a lightweight reward model with contrastive ranking loss, AdaRewriter selects the most promising reformulation during inference. Notably, it can operate effectively in black-box systems, including commercial LLM APIs. Experiments on five conversational search datasets show that AdaRewriter significantly outperforms the existing methods across most settings, demonstrating the potential of test-time adaptation for conversational query reformulation.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 37 of its 57 references that are in the map. First posted on arXiv 2 Jun 2025.
Builds on
37 of 57 references.
References · 37
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
- 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
- 2023Let's Verify Step by Stepcited by 3,789
- 2017Billion-scale similarity search with GPUscited by 2,497
- 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
- 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,464
- 2022Solving math word problems with process- and outcome-based feedbackcited by 901
- 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
- 2021SPLADE: Sparse Lexical and Expansion Model for First Stage Rankingcited by 286
- 2023Fine-Tuning LLaMA for Multi-Stage Text Retrievalcited by 272
25 more
- 2020Open-Domain Question Answering Goes Conversational via Question Rewritingcited by 148
- 2021SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarizationcited by 132
- 2024Fast Best-of-N Decoding via Speculative Rejectioncited by 112
- 2021TopiOCQA: Open-domain Conversational Question Answering with Topic Switchingcited by 96
- 2023Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Searchcited by 75
- 2021Few-Shot Conversational Dense Retrievalcited by 72
- 2023Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewritingcited by 69
- 2021CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learningcited by 68
- 2024HYDRA: Model Factorization Framework for Black-Box LLM Personalizationcited by 60
- 2023ConvGQR: Generative Query Reformulation for Conversational Searchcited by 59
- 2018Pytrec_eval: An Extremely Fast Python Interface to trec_evalcited by 46
- 2020Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Modelscited by 45
- 2021Contextualized Query Embeddings for Conversational Searchcited by 37
- 2024MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoningcited by 36
- 2024CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Searchcited by 29
- 2023Learning to Relate to Previous Turns in Conversational Searchcited by 26
- 2024Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversationcited by 23
- 2023IterCQR: Iterative Conversational Query Reformulation with Retrieval Guidancecited by 20
- 2024ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrievalcited by 19
- 2024Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentationcited by 17
- 2023Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answeringcited by 15
- 2024A Surprisingly Simple yet Effective Multi-Query Rewriting Method for Conversational Passage Retrievalcited by 14
- 2024AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignmentcited by 14
- 2024Interpreting Conversational Dense Retrieval by Rewriting-Enhanced Inversion of Session Embeddingcited by 13
- 2024SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decodingcited by 9
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning
- 2024Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers
- 2025ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answering
- 2026RAC: Retrieval-Augmented Clarification for Faithful Conversational Search
- 2025References Indeed Matter? Reference-Free Preference Optimization for Conversational Query Reformulation
- 2024Rewriting Conversational Utterances with Instructed Large Language Models
- 2025From Clicks to Preference: A Multi-stage Alignment Framework for Generative Query Suggestion in Conversational System
- 2024Generative Query Reformulation Using Ensemble Prompting, Document Fusion, and Relevance Feedback