Hideo Joho
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hideo Joho has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
- Hai-Tao Yu
Institute of Library, Information and Media Science, University of Tsukuba, Tsukuba, Japan
4 shared publications - Joemon M. Jose
University of Glasgow, Glasgow, United Kingdom
4 shared publications - Rahmi Rahmi
Universitas Indonesia
3 shared publications - Adam Jatowt
University of Innsbruck
2 shared publications - Cathal Gurrin
Dublin City University, Dublin, Ireland
2 shared publications - Chirag Shah
Information School, University of Washington, Seattle, WA, USA
2 shared publications
Latest Publications
- Open Access
- 24 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 82-93
Towards Adaptive and Retriever-friendly Retrieval-augmented Generation via Reinforcement Learning
- 24 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 82-93
Open AccessTowards Adaptive and Retriever-friendly Retrieval-augmented Generation via Reinforcement Learning
- 12 May 2026
- Published by Springer Nature
- p. 341-356
Retrieval-Augmented Diffusion Language Model for Generative Commonsense Reasoning
- 12 May 2026
- Published by Springer Nature
- p. 341-356
Retrieval-Augmented Diffusion Language Model for Generative Commonsense Reasoning
- Open Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 254-263
CollabSearch: A Study of User-LLM Collaboration in Task-Based Search
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 254-263
Open AccessCollabSearch: A Study of User-LLM Collaboration in Task-Based Search
- Open Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 431-433
Controlled Experimentation of Model Search Behaviour with Geniie-Lab
This half-day tutorial provides participants with a framework and hands-on experience for conducting controlled experiments on model search behaviour using an open-source toolkit. Participants will learn how to design, run, and analyse experiments to investigate behavioural differences across large language models. By integrating techniques from human user studies with LLM experimentation, the tutorial strengthens CHIIR’s methodological foundations and broadens its scope to include behavioural analysis of generative and agentic systems.
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 431-433
Open AccessControlled Experimentation of Model Search Behaviour with Geniie-Lab
This half-day tutorial provides participants with a framework and hands-on experience for conducting controlled experiments on model search behaviour using an open-source toolkit. Participants will learn how to design, run, and analyse experiments to investigate behavioural differences across large language models. By integrating techniques from human user studies with LLM experimentation, the tutorial strengthens CHIIR’s methodological foundations and broadens its scope to include behavioural analysis of generative and agentic systems.
- Open Access
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 396-405
Beyond Static Evaluation: Rethinking the Assessment of Personalized Agent Adaptability in Information Retrieval
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 396-405
Open AccessBeyond Static Evaluation: Rethinking the Assessment of Personalized Agent Adaptability in Information Retrieval
- Open Access
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 55-63
Geniie-Lab: A Testbed for Controlled Experimentation of Model Search Behaviour
- 6 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 55-63
Open AccessGeniie-Lab: A Testbed for Controlled Experimentation of Model Search Behaviour
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 3843-3852
An Instruction-Response Perspective on Large Language Models in Information Retrieval Tasks
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 3843-3852
Open AccessAn Instruction-Response Perspective on Large Language Models in Information Retrieval Tasks
- Open Access
- 24 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 292-297
Eliciting Implicit Information Needs in E-Commerce Search by Using the Think-Aloud Method
- 24 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 292-297
Open AccessEliciting Implicit Information Needs in E-Commerce Search by Using the Think-Aloud Method
- Open Access
- 11 March 2025
- Published by University of Borås
- Vol. 30 (iConf) , 1123-1130
Exploring the role of large language model in collaborative travel planning task
Introduction. This study explores how generative AI, specifically ChatGPT, influences collaborative travel planning. Understanding its effect on tasks like trip planning reveals insights into human-AI collaboration, particularly how AI tools support decision-making and streamline information gathering. Method. Twenty participants (10 pairs) planned a 1-night, 2-day trip under two conditions: (1) using only Google, and (2) using Google with ChatGPT. This within-subject study measured completion time, satisfaction, and plan quality via questionnaires and observation to capture task performance, user behaviour, and collaboration dynamics. Analysis. Data was analysed using t-tests and Wilcoxon signed-rank tests to compare completion times, satisfaction, and plan quality. Analyses of conversation volume and ChatGPT logs provided insights into AI-assisted collaboration dynamics and interaction patterns. Results. No significant difference in task completion time was found. However, plans made with ChatGPT were more complete and aligned with requirements. Participants found information more easily with ChatGPT, but satisfaction levels remained similar, suggesting that easier information access did not translate to higher satisfaction. Conclusions. Generative AI improves collaborative search task quality but does not enhance efficiency or satisfaction. AI tools like ChatGPT are effective for providing structured information and are best used as complementary resources alongside traditional search engines in planning tasks.
- 11 March 2025
- Published by University of Borås
- Vol. 30 (iConf) , 1123-1130
Open AccessExploring the role of large language model in collaborative travel planning task
Introduction. This study explores how generative AI, specifically ChatGPT, influences collaborative travel planning. Understanding its effect on tasks like trip planning reveals insights into human-AI collaboration, particularly how AI tools support decision-making and streamline information gathering. Method. Twenty participants (10 pairs) planned a 1-night, 2-day trip under two conditions: (1) using only Google, and (2) using Google with ChatGPT. This within-subject study measured completion time, satisfaction, and plan quality via questionnaires and observation to capture task performance, user behaviour, and collaboration dynamics. Analysis. Data was analysed using t-tests and Wilcoxon signed-rank tests to compare completion times, satisfaction, and plan quality. Analyses of conversation volume and ChatGPT logs provided insights into AI-assisted collaboration dynamics and interaction patterns. Results. No significant difference in task completion time was found. However, plans made with ChatGPT were more complete and aligned with requirements. Participants found information more easily with ChatGPT, but satisfaction levels remained similar, suggesting that easier information access did not translate to higher satisfaction. Conclusions. Generative AI improves collaborative search task quality but does not enhance efficiency or satisfaction. AI tools like ChatGPT are effective for providing structured information and are best used as complementary resources alongside traditional search engines in planning tasks.
- Open Access
- 8 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 249-258
Effect of LLM's Personality Traits on Query Generation
Large language models (LLMs) have demonstrated strong performance across various natural language processing tasks and are increasingly integrated into daily life. Just as personality traits are crucial in human communication, they could also play a significant role in the behavior of LLMs, for instance, in the context of Retrieval Augmented Generation. Previous studies have shown that Big Five personality traits could be applied to LLMs, but their specific effects on information retrieval tasks have not been sufficiently explored. This study aims to examine how personality traits assigned to LLM agents affect their query formulation behavior and search performance. We propose a method to accurately assign personality traits to LLM agents based on the Big Five theory and verify its accuracy using the IPIP-NEO-120 scale. We then design a query generation experiment using the NTCIR Ad-Hoc test collections and evaluate the search performance of queries generated by different LLM agents. The results show that our method successfully assigns all five personality traits to LLM agents as intended. Additionally, the query generation experiment suggests that the assigned traits did influence the length and vocabulary choices of generated queries. Finally, the retrieval effectiveness of the traits varied across test collections, showing a relative improvement ranging from -7.7% to +4.6%, but these differences were not statistically significant.
- 8 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 249-258
Open AccessEffect of LLM's Personality Traits on Query Generation
Large language models (LLMs) have demonstrated strong performance across various natural language processing tasks and are increasingly integrated into daily life. Just as personality traits are crucial in human communication, they could also play a significant role in the behavior of LLMs, for instance, in the context of Retrieval Augmented Generation. Previous studies have shown that Big Five personality traits could be applied to LLMs, but their specific effects on information retrieval tasks have not been sufficiently explored. This study aims to examine how personality traits assigned to LLM agents affect their query formulation behavior and search performance. We propose a method to accurately assign personality traits to LLM agents based on the Big Five theory and verify its accuracy using the IPIP-NEO-120 scale. We then design a query generation experiment using the NTCIR Ad-Hoc test collections and evaluate the search performance of queries generated by different LLM agents. The results show that our method successfully assigns all five personality traits to LLM agents as intended. Additionally, the query generation experiment suggests that the assigned traits did influence the length and vocabulary choices of generated queries. Finally, the retrieval effectiveness of the traits varied across test collections, showing a relative improvement ranging from -7.7% to +4.6%, but these differences were not statistically significant.