Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewriting

Ranked by how close their title and abstract are to this paper’s. Select some to read them together.

Closest papers

1. Very close Broader context Not relevant

   Query Understanding in the Age of Large Language Models

   Avishek Anand, V. Venktesh, Abhijit Anand et al. · 2023 · arXiv.org · preprint, not peer reviewed · cited 13 times · Not summarized yet

   Query Understanding proposes an interactive LLM query-rewriting framework that makes search intent explicit and editable before retrieval.

   Abstract

   Querying, conversing, and controlling search and information-seeking interfaces using natural language are fast becoming ubiquitous with the rise and adoption of large-language models (LLM). In this position paper, we describe a generic framework for interactive query-rewriting using LLMs. Our proposal aims to unfold new opportunities for improved and transparent intent understanding while building high-performance retrieval systems using LLMs. A key aspect of our framework is the ability of the rewriter to fully specify the machine intent by the search engine in natural language that can be further refined, controlled, and edited before the final retrieval phase. The ability to present, int…

2. Very close Broader context Not relevant

   LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency

   Zhaodonghui Li, Haitao Yuan, Huiming Wang et al. · 2024 · Databases · cited 71 times · AI summary available

   LLM-R2 uses an LLM to select rule-based rewrites of SQL queries while preserving results, rather than rewriting conversational search queries for retrieval.

   Abstract

   Query rewrite, which aims to generate more efficient queries by altering a SQL query's structure without changing the query result, has been an important research problem. In order to maintain equivalence between the rewritten query and the original one during rewriting, traditional query rewrite methods always rewrite the queries following certain rewrite rules. However, some problems still remain. Firstly, existing methods of finding the optimal choice or sequence of rewrite rules are still limited and the process always costs a lot of resources. Methods involving discovering new rewrite rules typically require complicated proofs of structural logic or extensive user interactions. Secondly…

3. Very close Another approach to the problem Not relevant

   Crafting the Path: Robust Query Rewriting for Information Retrieval

   Ingeol Baek, Ji-Min Lee, Joonho Yang et al. · 2024 · IEEE Access · cited 16 times · Not summarized yet

   Crafting the Path structures LLM-generated rewrites for information retrieval, addressing missing model knowledge rather than emphasizing informative conversational rewrites.

   Abstract

   Query rewriting aims to generate a new query that can complement the original query to improve the information retrieval system. Recent studies on query rewriting, such as query2doc, query2expand and querey2cot, rely on the internal knowledge of Large Language Models (LLMs) to generate a relevant passage to add information to the query. Nevertheless, the efficacy of these methodologies may markedly decline in instances where the requisite knowledge is not encapsulated within the model’s intrinsic parameters. In this paper, we propose a novel structured query rewriting method called Crafting The Path tailored for retrieval systems. Crafting The Path involves a three-step process that crafts q…

4. Very close Another approach to the problem Not relevant

   Context Aware Query Rewriting for Text Rankers using LLM

   Abhijit Anand, Venktesh V, Vinay Setty et al. · 2023 · Information Retrieval · preprint, not peer reviewed · cited 27 times · AI summary available

   Context Aware Query Rewriting studies LLM rewrites for text ranking and identifies limitations such as concept drift, a related retrieval task.

   Abstract

   Query rewriting refers to an established family of approaches that are applied to underspecified and ambiguous queries to overcome the vocabulary mismatch problem in document ranking. Queries are typically rewritten during query processing time for better query modelling for the downstream ranker. With the advent of large-language models (LLMs), there have been initial investigations into using generative approaches to generate pseudo documents to tackle this inherent vocabulary gap. In this work, we analyze the utility of LLMs for improved query rewriting for text ranking tasks. We find that there are two inherent limitations of using LLMs as query re-writers -- concept drift when using onl…

5. Very close Another approach to the problem Not relevant

   LiRe: Efficient Query Rewriting for Retrieval Augmented Generation Systems

   Chengfeng Chen, Xiao-Dong Huang, Yangzhen Xu et al. · 2024 · 2024 4th International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Techno · cited 1 time · Not summarized yet

   LiRe offers a lightweight, training-free, retrieval-oriented rewrite system for RAG, rather than the paper’s LLM instruction, editing, and distillation approach.

   Abstract

   With the continuous advancement of information retrieval technologies, query rewriting has become a key technique for enhancing retrieval effectiveness. In the context of the widespread application of large language models and retrieval-augmented generation technologies, high-quality query rewriting plays a crucial role in tasks like open-domain question answering. Conventional Conversational Query Rewriting (CQR) methods often prioritize human-friendly query formulation, which may not consistently produce optimal retriever-friendly results. To address this limitation, we present LiRe, a lightweight and training-free query rewriting system. LiRe employs a retrieval-oriented strategy to refin…

6. Very close Another approach to the problem Not relevant

   Contextualizing Search Queries In-Context Learning for Conversational Rewriting with LLMs

   Raymond Wilson, Chase Carter, Cole Graham · 2025 · arXiv.org · preprint, not peer reviewed · cited 6 times · Not summarized yet

   Contextualizing Search Queries uses few-shot in-context learning to produce standalone conversational queries without fine-tuning.

   Abstract

   Conversational query rewriting is crucial for effective conversational search, yet traditional supervised methods require substantial labeled data, which is scarce in low-resource settings. This paper introduces Prompt-Guided In-Context Learning, a novel approach that leverages the in-context learning capabilities of Large Language Models (LLMs) for few-shot conversational query rewriting. Our method employs carefully designed prompts, incorporating task descriptions, input/output format specifications, and a small set of illustrative examples, to guide pre-trained LLMs to generate context-independent queries without explicit fine-tuning. Extensive experiments on benchmark datasets, TREC and…

7. Very close Builds on this paper Cites this paper Not relevant

   ChatGPT Versus Modest Large Language Models: An Extensive Study on Benefits and Drawbacks for Conversational Search

   Guido Rocchietti, Cosimo Rulli, Franco Maria Nardini et al. · 2025 · IEEE Access · cited 3 times · Not summarized yet

   ChatGPT Versus Modest Large Language Models studies prompted and fine-tuned LLM rewriting for conversational search, and cites this paper.

   Abstract

   Large Language Models (LLMs) are effective in modeling text syntactic and semantic content, making them a strong choice to perform conversational query rewriting. While previous approaches proposed NLP-based custom models, requiring significant engineering effort, our approach is straightforward and conceptually simpler. Not only do we improve effectiveness over the current state-of-the-art, but we also curate the cost and efficiency aspects. We explore the use of pre-trained LLMs fine-tuned to generate quality user query rewrites, aiming to reduce computational costs while maintaining or improving retrieval effectiveness. As a first contribution, we study various prompting approaches — incl…

8. Very close Another approach to the problem Not relevant

   Think Then Rewrite: Reasoning Enhanced Query Rewriting for Domain Specific Retrieval

   Ang Li, Yu-Fei Shi, Yuxuan Si et al. · 2026 · AAAI Conference on Artificial Intelligence · cited 4 times · Not summarized yet

   Think Then Rewrite uses reinforcement learning to reason through ambiguous domain-specific queries before rewriting them for retrieval.

   Abstract

   Query rewriting is a crucial task for improving retrieval, especially in professional domains such as law and medicine, where user queries are often underspecified and ambiguous. While large language models (LLMs) offer strong understanding and generation capabilities, existing LLM-based approaches reduce the task to text transformation or expansion, neglecting reasoning to disambiguate queries, which fails to bridge the cognitive gap between user queries and specialized documents. In this paper, we propose Think-Then-Rewrite (TTR), a reinforcement learning based framework that unleashes LLMs' reasoning ability for domain-specific query rewriting. TTR introduces a contrastive mutual informat…

Prior work it builds on

1. Close Groundwork for this paper Used in depth by this paper A method it uses Not relevant

   ConvGQR: Generative Query Reformulation for Conversational Search

   Fengran Mo, Ke-Long Mao, Yutao Zhu et al. · 2023 · Annual Meeting of the Association for Computational Linguistics · cited 150 times · Not summarized yet

   ConvGQR addresses the problem of human rewrites being suboptimal and adds potential-answer information to conversational query reformulation; this paper cites it.

   Abstract

   In conversational search, the user’s real search intent for the current conversation turn is dependent on the previous conversation history. It is challenging to determine a good search query from the whole conversation context. To avoid the expensive re-training of the query encoder, most existing methods try to learn a rewriting model to de-contextualize the current query by mimicking the manual query rewriting.However, manually rewritten queries are not always the best search queries.Thus, training a rewriting model on them would lead to sub-optimal queries. Another useful information to enhance the search query is the potential answer to the question. In this paper, we propose ConvGQR, a…

2. Close Groundwork for this paper Used in depth by this paper A method it uses Not relevant

   Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting

   Sheng-Chieh Lin, Jheng-Hong Yang, Rodrigo Nogueira et al. · 2021 · ACM Trans. Inf. Syst. · cited 117 times · Not summarized yet

   Multi-Stage Conversational Passage Retrieval combines term-importance estimation and neural query rewriting to resolve conversational query ambiguity; this paper cites it.

   Abstract

   Conversational search plays a vital role in conversational information seeking. As queries in information seeking dialogues are ambiguous for traditional ad hoc information retrieval (IR) systems due to the coreference and omission resolution problems inherent in natural language dialogue, resolving these ambiguities is crucial. In this article, we tackle conversational passage retrieval, an important component of conversational search, by addressing query ambiguities with query reformulation integrated into a multi-stage ad hoc IR system. Specifically, we propose two conversational query reformulation (CQR) methods: (1) term importance estimation and (2) neural query rewriting. For the form…

3. Very close Groundwork for this paper Not relevant

   Explicit Query Rewriting for Conversational Dense Retrieval

   Hong-Jin Qian, Zhicheng Dou · 2022 · Conference on Empirical Methods in Natural Language Processing · cited 76 times · Not summarized yet

   Explicit Query Rewriting unifies query rewriting with contextualized retrieval representations for conversational dense retrieval; this paper cites it.

   Abstract

   In a conversational search scenario, a query might be context-dependent because some words are referred to previous expressions or omitted. Previous works tackle the issue by either reformulating the query into a self-contained query (query rewriting) or learning a contextualized query embedding from the query context (context modelling). In this paper, we propose a model CRDR that can perform query rewriting and context modelling in a unified framework in which the query rewriting’s supervision signals further enhance the context modelling. Instead of generating a new query, CRDR only performs necessary modifications on the original query, which improves both accuracy and efficiency of quer…

4. Close Groundwork for this paper Used in depth by this paper A method it uses Not relevant

   Open-Domain Question Answering Goes Conversational via Question Rewriting

   R. Anantha, Svitlana Vakulenko, Zhucheng Tu et al. · 2020 · North American Chapter of the Association for Computational Linguistics · cited 286 times · Not summarized yet

   Open-Domain Question Answering Goes Conversational introduces QReCC, the dataset used to evaluate this paper’s informative query rewrites.

   Abstract

   We introduce a new dataset for Question Rewriting in Conversational Context (QReCC), which contains 14K conversations with 80K question-answer pairs. The task in QReCC is to find answers to conversational questions within a collection of 10M web pages (split into 54M passages). Answers to questions in the same conversation may be distributed across several web pages. QReCC provides annotations that allow us to train and evaluate individual subtasks of question rewriting, passage retrieval and reading comprehension required for the end-to-end conversational question answering (QA) task. We report the effectiveness of a strong baseline approach that combines the state-of-the-art model for ques…

5. Close Groundwork for this paper Not relevant

   Few-Shot Generative Conversational Query Rewriting

   S. Yu, Jiahua Liu, Jingqin Yang et al. · 2020 · Annual International ACM SIGIR Conference on Research and Development in Information Retrieval · cited 233 times · Not summarized yet

   Few-Shot Generative Conversational Query Rewriting fine-tunes GPT-2 using weak supervision and limited manual rewrites; this paper cites it.

   Abstract

   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…

Papers that cite it

1. Very close Builds on this paper Uses this paper in depth Not relevant

   CompCQR: Compositional Query Generation for Training-Free Conversational Search

   Yunah Jang, Kang-il Lee, Joongbo Shin et al. · 2026 · Not summarized yet

   CompCQR develops training-free compositional query generation for conversational search and cites this paper.

   Abstract

   Multi-turn interactions with LLMs are becoming increasingly common in information-seeking scenarios. However, user queries are often ambiguous and context-dependent, making them ill-suited for direct use as retriever queries. Conversational query reformulation (CQR) addresses this issue by rewriting the current utterance into a stand-alone query grounded in the dialogue history. Recent LLM-based CQR approaches achieve strong performance; however, their repeated LLM invocations and misalignment with downstream retrievers remain challenges. In this work, we begin from the observation that retrievers are highly sensitive to content ordering: simply reordering the same content can lead to change…

2. Very close Builds on this paper Not relevant

   RaFe: Ranking Feedback Improves Query Rewriting for RAG

   Shengyu Mao, Yong Jiang, Boli Chen et al. · 2024 · Conference on Empirical Methods in Natural Language Processing · cited 93 times · Not summarized yet

   RaFe trains query rewriters using ranking feedback without annotations and cites this paper.

   Abstract

   As Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved, query rewriting has been widely incorporated into the RAG system for downstream tasks like open-domain QA. Many works have attempted to utilize small models with reinforcement learning rather than costly LLMs to improve query rewriting. However, current methods require annotations (e.g., labeled relevant documents or downstream answers) or predesigned rewards for feedback, which lack generalization, and fail to utilize signals tailored for query rewriting. In this paper, we propose ours, a framework for training query rewriting models free of annotations. By leveraging a publicly available re…

3. Close Broader context Uses this paper in depth Not relevant

   Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA

   Nirmal Roy, Leonardo F. R. Ribeiro, Rexhina Blloshmi et al. · 2024 · Computation and Language · cited 25 times · AI summary available

   Learning When to Retrieve studies retrieval decisions and responses in conversational QA, a broader RAG problem that includes query rewriting.

   Abstract

   Augmenting Large Language Models (LLMs) with information retrieval capabilities (i.e., Retrieval-Augmented Generation (RAG)) has proven beneficial for knowledge-intensive tasks. However, understanding users' contextual search intent when generating responses is an understudied topic for conversational question answering (QA). This conversational extension leads to additional concerns when compared to single-turn QA as it is more challenging for systems to comprehend conversational context and manage retrieved passages over multiple turns. In this work, we propose a method for enabling LLMs to decide when to retrieve in RAG settings given a conversational context. When retrieval is deemed nec…

4. Very close Builds on this paper Not relevant

   MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language Models

   Yu-Jing Wang, Hainan Zhang, Liang Pang et al. · 2024 · AAAI Conference on Artificial Intelligence · cited 23 times · Not summarized yet

   MaFeRw uses multiple feedback signals to train query rewriting for RAG and cites this paper.

   Abstract

   In a real-world RAG system, the current query often involves spoken ellipses and ambiguous references from dialogue contexts, necessitating query rewriting to better describe user's information needs. However, traditional context-based rewriting has minimal enhancement on downstream generation tasks due to the lengthy process from query rewriting to response generation. Some researchers try to utilize reinforcement learning with generation feedback to assist the rewriter, but this sparse rewards provide little guidance in most cases, leading to unstable training and generation results.We find that user's needs are also reflected in the gold documents, retrieved documents and ground-truth. Th…

5. Close Builds on this paper Uses this paper in depth Not relevant

   DVCQR: Dual-View Conversational Query Rewriting with Stage-wise Reinforcement Learning

   Chen-Yi Li, Xinhui Tu, Zaixiang Wang · 2026 · Annual Meeting of the Association for Computational Linguistics · cited 2 times · Not summarized yet

   DVCQR creates separate sparse- and dense-oriented conversational rewrites to address retriever preferences and cites this paper.

   Abstract

   Conversational query rewriting (CQR) addresses context dependence in conversational search by rewriting each user query into a standalone form. Recent approaches leverage reinforcement learning (RL) to directly optimize retrieval effectiveness; however, they typically rely on a single rewrite, which struggles to accommodate the divergent preferences of sparse and dense retrievers and often suffers from conflicting optimization signals. We pro-pose DVCQR, a Dual-View CQR framework that explicitly generates two complementary rewrites for each query: a sparse-view rewrite that emphasizes distinctive lexical anchors, and a dense-view rewrite that captures complete semantic constraints. Both rewr…