EMNLP Findings2023
Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewriting
Fanghua Ye, Meng Fang, Shenghui Li, Emine Yilmaz
Abstract
Query rewriting plays a vital role in enhancing conversational search by transforming contextdependent user queries into standalone forms.Existing approaches primarily leverage humanrewritten queries as labels to train query rewriting models.However, human rewrites may lack sufficient information for optimal retrieval performance.To overcome this limitation, we propose utilizing large language models (LLMs) as query rewriters, enabling the generation of informative query rewrites through well-designed instructions.We define four essential properties for well-formed rewrites and incorporate all of them into the instruction.In addition, we introduce the role of rewrite editors for LLMs when initial query rewrites are available, forming a "rewrite-then-edit" process.Furthermore, we propose distilling the rewriting capabilities of LLMs into smaller models to reduce rewriting latency.Our experimental evaluation on the QReCC dataset demonstrates that informative query rewrites can yield substantially improved retrieval performance compared to human rewrites, especially with sparse retrievers. 1 Instruction to prompt LLM as rewrite editorGiven a question and its context, decontextualize the question by addressing coreference and omission issues.The resulting question should retain its original meaning and be as informative as possible, and should not duplicate any previously asked questions in the context.Q: Who proposed that atoms are the basic units of matter?A: John Dalton proposed that each chemical element is composed of atoms of a single, unique type, and they can combine to form more complex structures called chemical compounds.Question: How did the proposal come about?Rewrite: How did John Dalton's proposal that each chemical element is composed of atoms of a single unique type, and they can combine to form more complex structures called chemical compounds come about?Q: Who proposed that atoms are the basic units of matter?A: John Dalton proposed that each chemical element is composed of atoms of a single, unique type, and they can combine to form more complex structures called chemical compounds.Question: How did the proposal come about?Rewrite: How did John Dalton's proposal come about?Edit: How did John Dalton's proposal that each chemical element is composed of atoms of a single unique type, and they can combine to form more complex structures called chemical compounds come about?Q: What job did Elizabeth Blackwell have?A: A lecturer in midwifery.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
20 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- LoRA: Low-Rank Adaptation of Large Language Models cites Language Models are Few-Shot Learners
- Think Then Embed: Generative Context Improves Multimodal Embedding cites LoRA: Low-Rank Adaptation of Large Language Models
- Finetuned Language Models are Zero-Shot Learners cites Language Models are Few-Shot Learners
- Finetuned Language Models are Zero-Shot Learners cites Training language models to follow instructions with human feedback
- Training language models to follow instructions with human feedback cites Finetuned Language Models are Zero-Shot Learners
- Training language models to follow instructions with human feedback cites Language Models are Few-Shot Learners
- UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations cites LoRA: Low-Rank Adaptation of Large Language Models
- UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations cites Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
- ChatQA: Surpassing GPT-4 on Conversational QA and RAG cites Finetuned Language Models are Zero-Shot Learners
- ChatQA: Surpassing GPT-4 on Conversational QA and RAG cites Training language models to follow instructions with human feedback
- Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation cites Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
Cited by top-tier papers20
- ChatQA: Surpassing GPT-4 on Conversational QA and RAGZihan Liu, Wei Ping, Rajarshi Roy, Peng Xu et al.NeurIPS 2024 · 121 citations
- Think Then Embed: Generative Context Improves Multimodal EmbeddingXuanming Cui, Jianpeng Cheng, Hong-You Chen, Satya Narayan Shukla et al.ICLR 2026 · 41 citations
- UniConv: Unifying Retrieval and Response Generation for Large Language Models in ConversationsFengran Mo, Yifan Gao, Chuan Meng, Xin Liu et al.ACL 2025 · 22 citations
- MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language ModelsYujing Wang, Hainan Zhang, Liang Pang, Binghui Guo et al.AAAI 2025 · 15 citations
- Generalizing Conversational Dense Retrieval via LLM-Cognition Data AugmentationHaonan Chen, Zhicheng Dou, Kelong Mao, Jiongnan Liu et al.ACL 2024 · 10 citations
Builds on26
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- Finetuned Language Models are Zero-Shot LearnersJason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu et al.ICLR 2022 · 4,966 citations
- Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text RetrievalLee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang et al.ICLR 2021 · 1,547 citations
Related papers
- Query Rewriting in Retrieval-Augmented Large Language ModelsXinbei Ma, Yeyun Gong, Pengcheng He, Hai Zhao et al.EMNLP 2023 · 191 citations
- Think Then Rewrite: Reasoning Enhanced Query Rewriting for Domain Specific RetrievalAng Li, Yufei Shi, Yuxuan Si, Yiquan Wu et al.AAAI 2026
- RaFe: Ranking Feedback Improves Query Rewriting for RAGShengyu Mao, Yong Jiang, Boli Chen, Xiao Li et al.EMNLP Findings 2024 · 19 citations
- GenRewrite: Query Rewriting via Large Language ModelsJie Liu, Barzan MozafariSIGMOD 2026 · 27 citations
- ConvGQR: Generative Query Reformulation for Conversational SearchFengran Mo, Kelong Mao, Yutao Zhu, Yihong Wu et al.ACL 2023 · 29 citations
