Query understanding in Conversational Information Seeking (CIS) involves accurately interpreting user intent through context-aware interactions. This includes resolving ambiguities, refining queries, and adapting to evolving information needs. Large Language Models (LLMs) enhance this process by interpreting nuanced language and adapting dynamically, improving the relevance and precision of search results in real-time. In this tutorial, we explore advanced techniques to enhance query understanding in LLM-based CIS systems. We delve into LLM-driven methods for developing robust evaluation metrics to assess query understanding quality in multi-turn interactions, strategies for building more interactive systems, and applications like proactive query management and query reformulation. We also discuss key challenges in integrating LLMs for query understanding in conversational search systems and outline future research directions. Our goal is to deepen the audience’s understanding of LLM-based conversational query understanding and inspire discussions to drive ongoing advancements in this field.
Our tutorial was held from 14:00-17:30 on July 13 (all the times are based on CET = Central European time).
| Time | Section | Slides |
|---|---|---|
| 14:00—14:15 | Section 1: Introduction and Background | [Slides] |
| 14:15—14:50 | Section 2: LLM-based Query Enhancement | [Slides] |
| 14:50—15:15 | Section 3: LLM-based Proactive Query Management | [Slides] |
| 15:15—15:20 | Q & A Session I | [Slides] |
| 15:30—16:00 | Coffee Break | [Slides] |
| 16:00—16:30 | Section 4: LLM-based Conversational Interaction | [Slides] |
| 16:30—17:10 | Section 5: Conversational Query Understanding Evaluation | [Slides] |
| 17:10—17:25 | Section 6: Summary and Outlook | [Slides] |
| 17:25—17:30 | Q & A Session II |
Yifei Yuan is a Postdoctoral Researcher at ETH Zürich and the University of Copenhagen. She received her Ph.D. degree from the Chinese University of Hong Kong in 2023. Her research interests lie in NLP and IR, especially for conversational interactive search systems and image-text-based multimodal learning. She has published more than 20 papers on relevant topics at top conferences in NLP and IR. She has been serving as an area chair or program committee member of mainstream machine learning venues such as ICLR, ACL, SIGIR, and WWW.
Zahra Abbasiantaeb is a second-year Ph.D. student at the Information Retrieval Lab (IRLab), University of Amsterdam (UvA). She received her master's degree from Amirkabir University (Tehran), on Artificial Intelligence in 2021. Her research interests lie in IR and CIS systems. She has published several papers at top conferences including SIGIR and WSDM. She is co-organizing the interactive Knowledge Assistant Track (iKAT) at the Text REtrieval Conference (TREC), aiming to advance the development of personalized conversational search systems.
Mohammad Aliannejadi is an Assistant Professor at IRLab, University of Amsterdam. His research interests include conversational information access, recommender systems, and LLM-based data augmentation and evaluation. Mohammad has co-organized various evaluation campaigns such as TREC CAsT, TREC iKAT, CLEF Touché, ConvAI3, and IGLU, focusing on different aspects of user interaction with conversational agents. Moreover, Mohammad has held multiple tutorials and lectures on CIS, such as ECIR, SIGIR-AP, WSDM, CHIIR, SIKS, and ASIRF.
Yang Deng is an Assistant Professor at Singapore Management University. His research lies in NLP and IR, especially for conversational and interactive systems. He has published over 50 papers on relevant topics at top venues such as WWW, SIGIR, ACL, EMNLP, and ICLR, and serves as Area Chair for ACL, EMNLP, and NAACL. He has rich experience in organizing tutorials at top conferences, including WWW 2024, SIGIR 2024, and ACL 2023. The tutorials at SIGIR 2024 and WWW 2024 both had the highest number of registrations among the conference participants.
@inproceedings{yuan2025query,
title={Query Understanding in LLM-based Conversational Information Seeking},
author={Yuan, Yifei and Abbasiantaeb, Zahra and Deng, Yang and Aliannejadi, Mohammad},
booktitle={Companion Proceedings of the ACM on Web Conference 2025},
year={2025}
}