Dr. Jiqun Liu, an Assistant Professor in the School of Library and Information Studies and an Affiliated Assistant Professor in the Department of Psychology at OU, is pioneering advancements in interactive information systems that transform how people search for, access, and engage with information in the era of Generative AI.
Dr. Jiqun Liu’s research combines machine learning (ML), human-AI interaction (HAI), and information retrieval (IR) to promote unbiased information access and enhance people’s informational well-being. His team aims to understand people’s cognitive limits, biases, and knowledge gaps that may hinder their interactions with text and conversational information systems and seeks to build and evaluate new AI-assisted systems that can better understand users’ intents, needs, and encountered challenges, and proactively mitigate their biases and address the negative impacts of misleading contents, model hallucination, and disinformation. Dr. Liu’s research informs the design of AI-driven search and recommendation systems, strengthens AI ethics and policy, and enhances reliable information access in critical domains such as healthcare, learning and education, and digital media. By integrating cognitive science, machine learning, and human-centered design, he is shaping next-generation AI systems that adapt to users, counter misinformation, and set new standards for responsible AI at scale.
Dr. Liu’s work is supported by a DISC seed funding project, which pushes the boundary in identifying user biases, evaluating search systems based on fairness metrics, and mitigating biases through fair and useful learning to rank (L2R) algorithms. His research contributions have been published at top-tier ACM venues, received best paper awards, and also presented in his research monograph titled “A Behavioral Economics Approach to Interactive Information Retrieval: Understanding and Supporting Boundedly Rational Users,” published by Springer Nature. Dr. Liu’s recent work on cognitive debiasing in information retrieval and prompting fair human-AI interactions has also been funded by the National Science Foundation (NSF) and Microsoft.
Far-Reaching Benefits:
· Smarter Search and Recommendations – Makes AI-driven commercial search engines and recommendation systems more relevant, fair, and user-aware.
· Safer AI Conversations – Reduces misinformation and bias in chatbots and conversational systems, ensuring more trustworthy AI interactions.
· Better Decisions in Critical Fields – Helps AI in healthcare, finance, and law provide more reliable, unbiased support.
· Stronger AI Ethics and Policy – Shapes industry standards and policies for fairer, socially responsible AI.
· Boosting Digital Resilience – Equips users to recognize bias and misleading content and navigate online information and knowledge more effectively.
List of Relevant Publications:
1. Liu, J. (2023). A behavioral economics approach to interactive information retrieval: Understanding and supporting boundedly rational users. Cham, Switzerland: Springer Nature. https://link.springer.com/book/10.1007/978-3-031-23229-9
Journal Articles:
1. Chen, N., Liu, J., Fang, H., Luo, Y., Sakai, T. & Wu, X. (2024). Decoy effect in search interaction: Understanding user behavior and measuring system vulnerability. ACM Transactions on Information Systems (TOIS). https://dl.acm.org/doi/pdf/10.1145/3708884
2. Wang, B. & Liu, J. (2023). Investigating the role of in-situ user expectation in Web search. Information Processing and Management. 60(3): 103300. (IP&M)
3. Liu, J. (2022). Toward Cranfield-inspired reusability assessment in interactive information retrieval evaluation. Information Processing and Management, 59(5), 103007. (IP&M)
Conference Papers:
1. Liu, J. & He, J. (2024). Boundedly rational searchers interacting with medical misinformation: Characterizing context-dependent decoy effects on credibility and usefulness evaluation in sessions. In Proceedings of the ACM SIGIR Conference on Human Information Interaction and Retrieval. New York, NY: ACM (CHIIR).
2. Chen, N., Liu, J., Dong, X. Liu, Q., Sakai, T. & Wu, X-M. (2024). AI can be cognitively biased: An exploratory study on threshold priming in LLM-based batch relevance assessment. In Proceedings of the 2nd International ACM SIGIR Conference on Information Retrieval in the Asia Pacific (SIGIR-AP).
3. Wang, B & Liu, J. (2024). Cognitively biased users interacting with algorithmically biased results in whole-session search on debated topics. In Proceedings of the ACM SIGIR Conference on the Theory of Information Retrieval. (ICTIR)
4. Chen, N., Liu, J., & Sakai, T. (2023). A reference-dependent model for Web search evaluation: Understanding and measuring the experience of boundedly rational users. In Proceedings of the ACM Web Conference 2023. (pp. 3396-3405). New York, NY: ACM. (WWW)
5. Liu, J. (2023). Toward a two-sided fairness framework in search and recommendation. In Proceedings of the ACM SIGIR Conference on Human Information Interaction and Retrieval. (pp.236-246). Austin, TX. (CHIIR)
6. Liu, J. & Shah, C. (2022). Leveraging user interaction signals and task state information in adaptively optimizing usefulness-oriented search sessions. In Proceedings of ACM/IEEE Joint Conference on Digital Libraries (pp. 1-11). Cologne, Germany. (JCDL)
