Project Assistant Professor
National Institute of Informatics, Tokyo
Researcher · Natural Language Processing
Hirokazu Kiyomaru
I am a researcher at the Research and Development Center for Large Language Models at the National Institute of Informatics. My work mainly focuses on developing, analyzing, and improving pre-training corpora for large language models.
Work Experience
Project Researcher
Kyoto University, Kyoto
Intern
Cookpad, Tokyo
Intern
Wantedly, Tokyo
Intern
Dwango Artificial Intelligence Laboratory, Tokyo
Education
Fukuyama Seishikan High School
Publications
Constructing a Japanese Verdict Prediction Dataset for Fact-Checking of LLM-Generated Texts
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL): Student Research Workshop, San Diego, California, USA, July 2026.
Constructing a Japanese Claim Decomposition Dataset for Fact-Checking of LLM-Generated Texts
In Proceedings of the Fifteenth Language Resources and Evaluation Conference, Palma, Mallorca, Spain, May 2026.
Scaling Data-Constrained Language Models with Synthetic Data
In Findings of the Association for Computational Linguistics: EACL 2026, Rabat, Morocco, March 2026.
Demystifying Mixed Outcomes of Self-Training: Pre-training Analyses on Non-Toy LLMs
In Findings of the Association for Computational Linguistics: EACL 2026, Rabat, Morocco, March 2026.
Optimizing Cost-Efficiency with LLM-Generated Training Data for Conversational Semantic Frame Analysis
In Proceedings of the 9th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL 2025), Albuquerque, New Mexico, USA, May 2025.
RecomMind: Movie Recommendation Dialogue with Seeker's Internal State
In Proceedings of the Second Workshop on Social Influence in Conversations (SICon 2024), Miami, Florida, USA, November 2024.
A Comprehensive Analysis of Memorization in Large Language Models
In Proceedings of the 17th International Natural Language Generation Conference (INLG), Tokyo, Japan, September 2024.
Abstractive Multi-Video Captioning: Benchmark Dataset Construction and Extensive Evaluation
In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING), Torino, Italy, May 2024.
MultiTool-CoT: GPT-3 Can Use Multiple External Tools with Chain of Thought Prompting
In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), Toronto, Canada, July 2023.
KWJA: A Unified Japanese Analyzer Based on Foundation Models
In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL): System Demonstrations, Toronto, Canada, July 2023.
Is a Knowledge-based Response Engaging?: An Analysis on Knowledge-Grounded Dialogue with Information Source Annotation
In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL): Student Research Workshop, Toronto, Canada, July 2023.
Minimally-Supervised Joint Learning of Event Volitionality and Subject Animacy Classification
In Proceedings of the AAAI Conference on Artificial Intelligence, 36(10), pp. 10921-10929, Online, February 2022.
Contextualized and Generalized Sentence Representations by Contrastive Self-Supervised Learning: A Case Study on Discourse Relation Analysis
In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), pp. 5578-5584, Online, June 2021.
A System for Worldwide COVID-19 Information Aggregation
In Proceedings of the 1st Workshop on NLP for COVID-19 (Part 2) at EMNLP 2020, Online, December 2020.
Diversity-aware Event Prediction based on a Conditional Variational Autoencoder with Reconstruction
In Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing (COIN), pp. 113-122, Hong Kong, China, November 2019.
Knowledge-based Dialog Approach for Exploring User's Intention
In Proceedings of FAIM/ISCA Workshop on Artificial Intelligence for Multimodal Human Robot Interaction, pp. 53-56, Stockholm, Sweden, 2018.
Cross-lingual Knowledge Projection Using Machine Translation and Target-side Knowledge Base Completion
In Proceedings of the 27th International Conference on Computational Linguistics (COLING), pp. 1508-1520, Santa Fe, New Mexico, USA, 2018.
BiCAmon: Activity monitoring tool on 3D connecome structures for various cognitive architectures
In Proceedings of Neuroinformatics 2016, pp 49-53, Reading, UK, 2016.
Awards
- The best paper award of ACL2023 Student Research Workshop (July 2023)
- The excellence award of the 29th annual meeting of the association for natural language processing (March 2023)
- The outstanding research award of the 253rd special interest group of natural language processing (September 2022)
- Doshisha University Undergraduate Awards for Distinction (February 2016)
- 1st Place - DHacks, a hackathon held at Doshisha University (September 2015)
- 1st Place - TOYOTA HSR Hackathon 2015 (September 2015)