🔥 News

• 2026.03:  🤗 Multilingual KokoroChat has been accepted to LREC 2026 and is now publicly available on GitHub!
• 2025.06:  📄 A journal paper has been accepted by the Journal of Natural Language Processing!
• 2025.06:  🤗 KokoroChat has been accepted to ACL 2025 main conference and is now publicly available on GitHub and Hugging Face!
• 2024.07:  📑 Long paper submitted to SIGDIAL2024 has been accepted!!

📖 Educations

• 2023.04 - 2026.03, Ph.D. in Informatics, The University of Electro-Communications, Tokyo, Japan.
• 2021.04 - 2023.03, M.S. in Informatics, The University of Electro-Communications, Tokyo, Japan.
• 2015.09 - 2019.06, B.S. in Software Engineering, Qingdao University of Science & Technology, Qingdao, China.

🤖 Competition Experience

• 2024.09 The 2nd Workshop of AI Werewolf and Dialog System at INLG 2024 (Team: UEC-IL — English Track: 1st/5, Japanese Track: 2nd/8)
• 2023.12 対話システムライブコンペティション6 シチュエーショントラック (Team: UECIL — 3rd/9)
• 2023.09 Natural Language Division of 5th International AIWolf Contest held at INLG 2023 (Team: sUper_IL — 1st/9)
• 2022.09 Protocol Division of 4th International AIWolf Contest held at IEEE Conference on Games 2022 (Team: sUper_IL — 3rd/49)

🎖 Honors and Awards

• 2026.03 言語処理学会第32回年次大会 (NLP2026) 優秀賞 (Selected 13/789 papers, acceptance rate ≈1.6%)
• 2024.09 The 2nd Workshop of AI Werewolf and Dialog System at INLG 2024 [award slide]
  • Best Win Rate and Game Action Award (Team: sUper_IL, Japanese and English Track)
  • Best Subjective Evaluation Award (Team: UEC-IL, English Track)
• 2024.09 第19回YANSシンポジウム ハッカソン YANS運営委員特別賞
• 2023.12 対話システムライブコンペティション6 シチュエーショントラック 優秀賞

📝 Publications

Journals

• JNLP Adapting Spoken Dialogue Systems to Low-Resource User Groups through Data Augmentation with a Focus on Dialogue Act Flow and Style Zhiyang Qi and Michimasa Inaba.
  Journal of Natural Language Processing, Vol.32, No.4, pp.1030-1061, 2025.

• TALLIP Collection and Analysis of Travel Agency Task Dialogues with Age-Diverse Speakers Michimasa Inaba, Yuya Chiba, Zhiyang Qi, Ryuichiro Higashinaka, Kazunori Komatani, Yusuke Miyao, and Takayuki Nagai.
  ACM Transactions on Asian and Low-Resource Language Information Processing, Vol.23, No.9, pp.1-23, 2024.
  Dataset

International Conferences (Refereed)

• LREC 2026 CORE B Multilingual KokoroChat: A Multi-LLM Ensemble Translation Method for Creating a Multilingual Counseling Dialogue Dataset Ryoma Suzuki, Zhiyang Qi, and Michimasa Inaba.
  GitHub Pages

• NCSP’26 Pathophysiological Classification Using Patients’ Subjective Pain Expressions Zhiyang Qi, Yuji Nozaki, Ryota Abe, Haruka Matsukura, Kazutoshi Fujibayashi, Toshio Naito, and Maki Sakamoto.
  Slide

• SIGDIAL 2025 CORE B Key Challenges in Multimodal Task-Oriented Dialogue Systems: Insights from a Large Competition-Based Dataset Shiki Sato, Shinji Iwata, Asahi Hentona, Yuta Sasaki, Takato Yamazaki, Shoji Moriya, Masaya Ohagi, Hirofumi Kikuchi, Jie Yang, Zhiyang Qi, Takashi Kodama, Akinobu Lee, Masato Komuro, Hiroyuki Nishikawa, Ryosaku Makino, Takashi Minato, Kurima Sakai, Tomo Funayama, Kotaro Funakoshi, Mayumi Usami, Michimasa Inaba, Tetsuro Takahashi, and Ryuichiro Higashinaka.

• SIGDIAL 2025 CORE B Analyzing Dialogue System Behavior in a Specific Situation Requiring Interpersonal Consideration Tetsuro Takahashi, Hirofumi Kikuchi, Jie Yang, Hiroyuki Nishikawa, Masato Komuro, Ryosaku Makino, Shiki Sato, Yuta Sasaki, Shinji Iwata, Asahi Hentona, Takato Yamazaki, Shoji Moriya, Masaya Ohagi, Zhiyang Qi, Takashi Kodama, Akinobu Lee, Takashi Minato, Kurima Sakai, Tomo Funayama, Kotaro Funakoshi, Mayumi Usami, Michimasa Inaba, and Ryuichiro Higashinaka.

• ACL 2025 CORE A* KokoroChat: A Japanese Psychological Counseling Dialogue Dataset Collected via Role-Playing by Trained Counselors Zhiyang Qi, Takumasa Kaneko, Keiko Takamizo, Mariko Ukiyo, and Michimasa Inaba.
  GitHub PagesPosterSlide

• IWSDS 2025 DSLCMM: A Multimodal Human-Machine Dialogue Corpus Built through Competitions Ryuichiro Higashinaka, Tetsuro Takahashi, Shinya Iizuka, Sota Horiuchi, Michimasa Inaba, Zhiyang Qi, Yuta Sasaki, Kotaro Funakoshi, Shoji Moriya, Shiki Sato, Takashi Minato, Kurima Sakai, Tomo Funayama, Masato Komuro, Hiroyuki Nishikawa, Ryosaku Makino, Hirofumi Kikuchi, and Mayumi Usami.

• AIWolfDial 2024 Enhancing Dialogue Generation in Werewolf Game Through Situation Analysis and Persuasion Strategies Zhiyang Qi and Michimasa Inaba.
  Slide

• AIWolfDial 2024 Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information Yoshiki Tanaka, Takumasa Kaneko, Hiroki Onozeki, Natsumi Ezure, Ryuichi Uehara, Zhiyang Qi, Tomoya Higuchi, Ryutaro Asahara, and Michimasa Inaba.

• YRRSDS 2024 Utilizing Large Language Models for Customized Dialogue Data Augmentation and Psychological Counseling Zhiyang Qi.
  PosterSlide

• SIGDIAL 2024 CORE B Data Augmentation Integrating Dialogue Flow and Style to Adapt Spoken Dialogue Systems to Low-Resource User Groups Zhiyang Qi and Michimasa Inaba.
  Poster

• IWSDS 2024 Dialogue System Live Competition Goes Multimodal: Analyzing the Effects of Multimodal Information in Situated Dialogue Systems Ryuichiro Higashinaka, Tetsuro Takahashi, Michimasa Inaba, Zhiyang Qi, Yuta Sasaki, Kotaro Funakoshi, Shoji Moriya, Shiki Sato, Takashi Minato, Kurima Sakai, Tomo Funayama, Masato Komuro, Hiroyuki Nishikawa, Ryosaku Makino, Hirofumi Kikuchi, and Mayumi Usami.

• INLG 2023 CORE B AIWolfDial 2023: Summary of Natural Language Division of 5th International AIWolf Contest Yoshinobu Kano, Neo Watanabe, Kaito Kagaminuma, Claus Aranha, Jaewon Lee, Benedek Hauer, Hisaichi Shibata, Soichiro Miki, Yuta Nakamura, Takuya Okubo, Soga Shigemura, Rei Ito, Kazuki Takashima, Tomoki Fukuda, Masahiro Wakutani, Tomoya Hatanaka, Mami Uchida, Mikio Abe, Akihiro Mikami, Takashi Otsuki, Zhiyang Qi, Kei Harada, Michimasa Inaba, Daisuke Katagami, Hirotaka Osawa, and Fujio Toriumi.

Preprints

• arXiv EmoStage: A Framework for Accurate Empathetic Response Generation via Perspective-Taking and Phase Recognition Zhiyang Qi, Keiko Takamizo, Mariko Ukiyo, and Michimasa Inaba.

• arXiv Enhancing Consistency in Multimodal Dialogue System Using LLM with Dialogue Scenario Hiroki Onozeki, Zhiyang Qi, Kazuma Akiyama, Ryutaro Asahara, Takumasa Kaneko, and Michimasa Inaba.
  Poster

Non-refereed

Report

• 学内セミナー 研究プロセスにおけるLLMの活用 -個人の実践例- 斉志揚（@生成AI・AI活用セミナー, 2025年7月14日）
  Slide

• SLUD SIGDIAL2024国際会議報告 斉志揚, 田中義規 (@第15回対話システムシンポジウム)
  Slide