Overview
Background
Hang is a Postdoctoral Research Fellow in IELab within the School of Electrical Engineering and Computer Science at the University of Queensland, Australia, where he works closely with Prof. Guido Zuccon, A/Prof. Bevan Koopman, and Dr. Ahmed Mourad. Prior to Ph.D, he received his Bachelor of Science degree in Computer Science at the University of Minnesota Twin-Cities, United States, 2016.
Hang's research interests span Information Retrieval (IR), Large Language Models (LLMs), Natural Language Processing (NLP), Agentic Search, Retrieval-Augmented Generation (RAG), and Machine Learning (ML). In particular, he is interested in developing intelligent search and information-access systems that combine effective retrieval with the reasoning and generation capabilities of LLMs. His research explores topics including neural and dense retrieval, retrieval enhancement and feedback, LLM-based relevance assessment, agentic and conversational search, RAG system design and evaluation, and the efficient and reliable integration of LLMs into real-world information retrieval pipelines.
Hang publishes at premier academic venues in IR (e.g. SIGIR, ECIR, WSDM, WWW, TOIS, IJDL). His work was supported by Grains Research and Development Corporation, through the AgAsk project during Ph.D.
Availability
- Dr Hang Li is:
- Available for supervision
Fields of research
Qualifications
- Bachelor of Computer Science, University of Minnesota-Twin Cities
- Doctor of Philosophy of Computer Science, The University of Queensland
Research interests
-
Information Retrieval and Search Systems
My research focuses on Information Retrieval (IR), including neural retrieval, dense and sparse retrieval, ranking and reranking, query representation, and relevance modelling. I am particularly interested in developing effective and efficient search systems that improve how users access and interact with large-scale information collections.
-
Large Language Models for Information Retrieval
I investigate the integration of Large Language Models (LLMs) into information retrieval systems, including LLM-based retrieval, reranking, query representation, relevance assessment, and search enhancement. My research explores how the reasoning and language understanding capabilities of LLMs can improve retrieval effectiveness while addressing challenges in efficiency, reliability, and evaluation.
-
Agentic Search and AI Agents
My research explores Agentic Search and LLM-based autonomous agents that can plan, search, reason over retrieved information, and iteratively refine their information-seeking strategies. I am interested in agentic information retrieval, deep research systems, tool-using agents, multi-step search, and the evaluation of agent behaviour and search trajectories.
-
Retrieval-Augmented Generation
I study Retrieval-Augmented Generation (RAG) systems that combine information retrieval with generative language models to produce grounded and contextually relevant responses. My work covers retrieval pipeline design, document and passage retrieval, generation, grounding, system evaluation, and the development of reliable RAG systems for real-world applications, including scientific and clinical information access.
-
Neural and Dense Information Retrieval
I develop neural retrieval methods based on learned representations and language models, with particular interests in dense retrieval, late interaction, query and document representation, pseudo-relevance feedback, and retrieval enhancement. My research investigates how richer representations and feedback signals can improve retrieval effectiveness while maintaining practical efficiency.
-
Evaluation of Search and Generative AI Systems
I investigate methods for evaluating modern information retrieval, RAG, and generative AI systems. This includes LLM-based relevance assessment, LLM-as-a-Judge methods, retrieval evaluation without extensive human labels, evaluation reliability and bias, and scalable approaches for assessing complex search and question-answering systems.
-
Natural Language Processing and Machine Learning
My broader research interests include Natural Language Processing (NLP) and Machine Learning (ML), particularly their application to information access, language understanding, question answering, and generative AI. I am interested in developing and applying machine learning methods that enable systems to retrieve, reason over, and generate information more effectively.
Works
Search Professor Hang Li’s works on UQ eSpace
2026
Conference Publication
When LLM Judges Inflate Scores: Exploring Overrating in Relevance Assessment
Yu, Chuting, Li, Hang, Zuccon, Guido, Mackenzie, Joel and Leelanupab, Teerapong (2026). When LLM Judges Inflate Scores: Exploring Overrating in Relevance Assessment. New York, NY, USA: ACM. doi: 10.1145/3805712.3809905
2026
Other Outputs
Advanced query representation and feedback methods for neural information retrieval
Li, Hang (2026). Advanced query representation and feedback methods for neural information retrieval. PhD Thesis, School of Electrical Engineering and Computer Science, The University of Queensland. doi: 10.14264/a3cd0b3
2026
Conference Publication
Evalugator — Rapid, agile development and evaluation of Retrieval Augmented Generation systems without labels
Koopman, Bevan, Li, Hang, Wang, Shuai and Zuccon, Guido (2026). Evalugator — Rapid, agile development and evaluation of Retrieval Augmented Generation systems without labels. 48th European Conference on Information Retrieval, ECIR 2026, Delft, The Netherlands, Mar 29 - Apr 02, 2026. Cham, Switzerland: Springer. doi: 10.1007/978-3-032-21321-1_8
2025
Other Outputs
Pseudo relevance feedback is enough to close the gap between small and large dense retrieval models
Li, Hang, Wang, Xiao, Koopman, Bevan and Zuccon, Guido (2025). Pseudo relevance feedback is enough to close the gap between small and large dense retrieval models. doi: 10.48550/arXiv.2503.14887
2025
Other Outputs
LLM-VPRF: Large language model based vector pseudo relevance feedback
Li, Hang, Zhuang, Shengyao, Koopman, Bevan and Zuccon, Guido (2025). LLM-VPRF: Large language model based vector pseudo relevance feedback. doi: 10.48550/arXiv.2504.01448
2024
Other Outputs
TPRF: A transformer-based pseudo-relevance feedback model for efficient and effective retrieval
Li, Hang, Yu, Chuting, Mourad, Ahmed, Koopman, Bevan and Zuccon, Guido (2024). TPRF: A transformer-based pseudo-relevance feedback model for efficient and effective retrieval. doi: 10.48550/arXiv.2401.13509
2024
Journal Article
AgAsk: an agent to help answer farmer’s questions from scientific documents
Koopman, Bevan, Mourad, Ahmed, Li, Hang, van der Vegt, Anton, Zhuang, Shengyao, Gibson, Simon, Dang, Yash, Lawrence, David and Zuccon, Guido (2024). AgAsk: an agent to help answer farmer’s questions from scientific documents. International Journal on Digital Libraries, 25 (4), 569-584. doi: 10.1007/s00799-023-00369-y
2023
Conference Publication
AgAsk: A conversational search agent for answering agricultural questions
Li, Hang, Koopman, Bevan, Mourad, Ahmed and Zuccon, Guido (2023). AgAsk: A conversational search agent for answering agricultural questions. 16th ACM International Conference on Web Search and Data Mining, WSDM 2023, Singapore, 27 - 3 March 2023. New York, NY United States: ACM. doi: 10.1145/3539597.3573034
2023
Conference Publication
MeSH suggester: a library and system for MeSH term suggestion for systematic review Boolean query construction
Wang, Shuai, Li, Hang and Zuccon, Guido (2023). MeSH suggester: a library and system for MeSH term suggestion for systematic review Boolean query construction. Sixteenth ACM International Conference on Web Search and Data Mining, Singapore, Singapore, 27 February - 3 March 2023. New York, NY, United States: ACM. doi: 10.1145/3539597.3573025
2023
Journal Article
Pseudo relevance feedback with deep language models and dense retrievers: successes and pitfalls
Li, Hang, Mourad, Ahmed, Zhuang, Shengyao, Koopman, Bevan and Zuccon, Guido (2023). Pseudo relevance feedback with deep language models and dense retrievers: successes and pitfalls. ACM Transactions on Information Systems, 41 (3) 62, 1-40. doi: 10.1145/3570724
2022
Conference Publication
Pseudo-relevance feedback with dense retrievers in Pyserini
Li, Hang, Zhuang, Shengyao, Ma, Xueguang, Lin, Jimmy and Zuccon, Guido (2022). Pseudo-relevance feedback with dense retrievers in Pyserini. ADCS '22: Australasian Document Computing Symposium, Adelaide, SA, Australia, 15-16 December 2022. New York, United States: Association for Computing Machinery. doi: 10.1145/3572960.3572982
2022
Conference Publication
Implicit feedback for dense passage retrieval: a counterfactual approach
Zhuang, Shengyao, Li, Hang and Zuccon, Guido (2022). Implicit feedback for dense passage retrieval: a counterfactual approach. 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), Madrid, Spain, 11 - 15 July 2022. New York, NY, United States: Association for Computing Machinery. doi: 10.1145/3477495.3531994
2022
Conference Publication
To Interpolate or not to Interpolate: PRF, dense and sparse retrievers
Li, Hang, Wang, Shuai, Zhuang, Shengyao, Mourad, Ahmed, Ma, Xueguang, Lin, Jimmy and Zuccon, Guido (2022). To Interpolate or not to Interpolate: PRF, dense and sparse retrievers. SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, 11-15 July 2022. New York, United States: Association for Computing Machinery. doi: 10.1145/3477495.3531884
2022
Conference Publication
How does feedback signal quality impact effectiveness of pseudo relevance feedback for passage retrieval
Li, Hang, Mourad, Ahmed, Koopman, Bevan and Zuccon, Guido (2022). How does feedback signal quality impact effectiveness of pseudo relevance feedback for passage retrieval. 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, 11 - 15 July 2022. New York, NY, United States: Association for Computing Machinery. doi: 10.1145/3477495.3531822
2022
Other Outputs
Agvaluate
Li, Hang, Zuccon, Guido, Koopman, Bevan and Mourad, Ahmed (2022). Agvaluate. The University of Queensland. (Dataset) doi: 10.48610/0160dc7
2022
Conference Publication
Improving query representations for dense retrieval with pseudo relevance feedback: a reproducibility study
Li, Hang, Zhuang, Shengyao, Mourad, Ahmed, Ma, Xueguang, Lin, Jimmy and Zuccon, Guido (2022). Improving query representations for dense retrieval with pseudo relevance feedback: a reproducibility study. 44th European Conference on IR Research, ECIR 2022, Stavanger, Norway, 10-14 April 2022. Cham, Switzerland: Springer International Publishing. doi: 10.1007/978-3-030-99736-6_40
2021
Conference Publication
MeSH Term Suggestion for Systematic Review Literature Search
Wang, Shuai, Li, Hang, Scells, Harrisen, Locke, Daniel and Zuccon, Guido (2021). MeSH Term Suggestion for Systematic Review Literature Search. Australasian Document Computing Symposium, Melbourne, VIC, Australia, 9 December 2021. New York, NY, United States: Association for Computing Machinery. doi: 10.1145/3503516.3503530
2021
Conference Publication
Deep query likelihood model for information retrieval
Zhuang, Shengyao, Li, Hang and Zuccon, Guido (2021). Deep query likelihood model for information retrieval. The 43rd European Conference On Information Retrieval (ECIR), Lucca, Italy - online event, March 28–April 1, 2021. Cham, Switzerland: Elsevier. doi: 10.1007/978-3-030-72240-1_49
2021
Journal Article
Design and research of intelligent question-answering(Q&A) system based on high school course knowledge graph
Yang, Zhijun, Wang, Yang, Gan, Jianhou, Li, Hang and Lei, Ning (2021). Design and research of intelligent question-answering(Q&A) system based on high school course knowledge graph. Mobile Networks and Applications, 26 (5), 1884-1890. doi: 10.1007/s11036-020-01726-w
2020
Conference Publication
Systematic review automation tools for end-to-end query formulation
Li, Hang, Scells, Harrisen and Zuccon, Guido (2020). Systematic review automation tools for end-to-end query formulation. SIGIR '20: The 43rd International ACM SIGIR conference on research and development in Information Retrieval, Virtual, July 2020. New York, NY USA: Association for Computing Machinery. doi: 10.1145/3397271.3401402
Supervision
Availability
- Dr Hang Li is:
- Available for supervision
Looking for a supervisor? Read our advice on how to choose a supervisor.
Supervision history
Current supervision
-
Doctor Philosophy
Evaluation of Agentic Information Retrieval Systems via Simulation for Next-Generation Search
Associate Advisor
Other advisors: Professor Guido Zuccon
Media
Enquiries
For media enquiries about Dr Hang Li's areas of expertise, story ideas and help finding experts, contact our Media team: