EMNLP Findings2023
Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search
Kelong Mao, Zhicheng Dou, Fengran Mo, Jiewen Hou, Haonan Chen, Hongjin Qian
Abstract
Precisely understanding users' contextual search intent has been an important challenge for conversational search. As conversational search sessions are much more diverse and long-tailed, existing methods trained on limited data still show unsatisfactory effectiveness and robustness to handle real conversational search scenarios. Recently, large language models (LLMs) have demonstrated amazing capabilities for text generation and conversation understanding. In this work, we present a simple yet effective prompting framework, called LLM4CS, to leverage LLMs as a textbased search intent interpreter to help conversational search. Under this framework, we explore three prompting methods to generate multiple query rewrites and hypothetical responses, and propose to aggregate them into an integrated representation that can robustly represent the user's real contextual search intent. Extensive automatic evaluations and human evaluations on three widely used conversational search benchmarks, including CAsT-19, CAsT-20, and CAsT-21, demonstrate the remarkable performance of our simple LLM4CS framework compared with existing methods and even using human rewrites. Our findings provide important evidence to better understand and leverage LLMs for conversational search. The code is released at https://github.com/ kyriemao/LLM4CS.
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.
22 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
- LLMIF: Augmented Large Language Model for Fuzzing IoT Devices cites Language Models are Few-Shot Learners
- LLMIF: Augmented Large Language Model for Fuzzing IoT Devices cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval cites ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
- Learning to Relate to Previous Turns in Conversational Search cites Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
- Learning to Relate to Previous Turns in Conversational Search cites ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
- Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent cites Language Models are Few-Shot Learners
- Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent cites Finetuned Language Models are Zero-Shot Learners
- Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent cites Chain-of-Thought Prompting Elicits Reasoning in 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 Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Cited by top-tier papers22
- MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval AugmentationHongjin Qian, Zheng Liu, Peitian Zhang, Kelong Mao et al.WWW 2025 · 92 citations
- LLMIF: Augmented Large Language Model for Fuzzing IoT DevicesJincheng Wang, Le Yu, Xiapu LuoS&P 2024 · 61 citations
- Learning to Relate to Previous Turns in Conversational SearchFengran Mo, Jian-Yun Nie, Kaiyu Huang, Kelong Mao et al.KDD 2023 · 16 citations
- Thought-Augmented Planning for LLM-Powered Interactive Recommender AgentHaocheng Yu, Yaxiong Wu, Hao Wang, Wei Guo et al.KDD 2026 · 16 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
Builds on18
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 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
- ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTOmar Khattab, Matei ZahariaSIGIR 2020 · 1,246 citations
Related papers
- Learning Contextual Retrieval for Robust Conversational SearchSeunghan Yang, Juntae Lee, Jihwan Bang, Kyuhong Shim et al.EMNLP 2025 · 3 citations
- CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational SearchFengran Mo, Abbas Ghaddar, Kelong Mao, Mehdi Rezagholizadeh et al.EMNLP 2024 · 9 citations
- ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense RetrievalKelong Mao, Chenlong Deng, Haonan Chen, Fengran Mo et al.EMNLP 2024 · 7 citations
- Agentic Conversational Search with Contextualized Reasoning via Reinforcement LearningFengran Mo, Yifan Gao, Sha Li, Hansi Zeng et al.ACL Findings 2026
- SSP: Self-Supervised Post-training for Conversational SearchQuan Tu, Shen Gao, Xiaolong Wu, Zhao Cao et al.ACL Findings 2023 · 1 citation
