Ryuto Koike (小池 隆斗)
PhD candidate at Tokyo Institute of Technology | Trustworthy NLP
Hello! I'm Ryuto, a second-year CS PhD candidate at Tokyo Institute of Technology. I'm honored to be advised by Prof. Naoaki Okazaki and working with Postdoc Masahiro Kaneko, and Prof. Preslav Nakov within MBZUAI (now remote).
My research lies at the intersection of Natural Language Processing(NLP) and Trustworthy AI: how can we build NLP systems that we can trust? I'm also interested in the difference between human writing and LLM writing, syntactically and semantically.
My previous work includes:
Detecting texts generated by Large Language Models (LLMs), particularly in increasing its robustness against adversarial attacks.
Enhancing LLM-based evaluation to be more reliable, particularly in mitigating its evaluation bias.
Actively looking for research collaborations, internships, and opportunities as a visiting student. Feel free to reach out to me! : ryuto.koike[at]nlp.c.titech.ac.jp
✨ News
May 2024: A paper accepted at ACL 2024 Findings on LLM-based evaluation @Bangkok🇹🇭.
Dec 2023: A paper accepted at AAAI 2024 on LLM detection @Vancouver🇨🇦.
Oct 2023: Our work on LLM detection was featured in Nikkei🗞.
Aug 2023: Received Double Sponsorship Awards at the YANS 2023🇯🇵.
Apr 2023: Joined Okazaki Lab, Tokyo Institute of Technology🇯🇵.
👨💻 Research and Work Experiences
Apr 2024 - Present: Research Collaborator Preslav Nakov's group, MBZUAI
Jan 2024 - Present: Research Engineer 3keigo.com
Apr 2023 - Present: Research Assistant Okazaki Lab, Tokyo Tech
Feb 2022 - Mar 2022: Machine Learning Engineer Intern Exawizards, Inc.
Sep 2021 - Jan 2022: Research Intern CyberAgent, Inc.
Jul 2021 - Aug 2021: Machine Learning Engineer Intern CyberAgent, Inc.
📜 Refereed Publications
Journal
A Support System for Generating YouTube Titles using Style Transfer
Ryuto Koike, Masafumi Hagiwara
Journal of Japan Society of Kansei Engineering (In Japanese)
[Paper]
International Conference
Likelihood-based Mitigation of Evaluation Bias in Large Language Models
Masanari Ohi, Masahiro Kaneko, Ryuto Koike, Mengsay Loem, Naoaki Okazaki
ACL 2024 (Findings, Acceptance rate: xx%)
[arXiv]
OUTFOX: LLM-generated Essay Detection through In-context Learning with Adversarially Generated Examples
Ryuto Koike, Masahiro Kaneko, Naoaki Okazaki
AAAI 2024 (Acceptance rate: 18.4%)
[Paper] [arXiv] [Data+Code] [Technical Appendix] [Video]
Preprint
🗣 Domestic Conference and Symposium (In Japanese)
Masanari Ohi, Masahiro Kaneko, Ryuto Koike, Mengsay Loem, Naoaki Okazaki. Likelihood-based Mitigation of Evaluation Bias in Large Language Models. The 30th Annual Meeting of The Association for Natural Language Processing (NLP2024). 2024. | Young Researcher’s Encouragement Award 🎉 |
Ryuto Koike, Masahiro Kaneko, Naoaki Okazaki. How You Prompt Matters! Even Task-Oriented Constraints in Instructions Affect LLM-Generated Text Detection. The 30th Annual Meeting of The Association for Natural Language Processing (NLP2024). 2024.
Ryuto Koike, Masahiro Kaneko, Naoaki Okazaki. OUTFOX: LLM-generated Essay Detection through In-context Learning with Adversarially Generated Examples. The 18th Symposium of Young Researcher Association for NLP Studies (YANS2023). 2023. | Sponsorship Awards 🎉: PKSHA Technology and HAKUHODO Technologies |
Ryuto Koike, Masafumi Hagiwara. A Support System for Generating YouTube Titles using Style Transfer. The 23rd Annual Meeting of Japan Society of Kansei Engineering. 2021.
🎓 Education
Apr 2023 - Present: Doctor of Engineering (Computer Science) Tokyo Institute of Technology
Apr 2021 - Mar 2023: Master of Engineering (Computer Science) Keio University
Apr 2017 - Mar 2021: Bachelor of Engineering (Computer Science) Keio University
🏆 Honors and Awards
Tokyo Tech SPRING Scholarship Awardee
Tokyo Institute of Technology, 2024-2026.
Scholarship: 2,160,000 JPY / APPROX 14,400 USD per year, Research Funds: 300,000 JPY / APPROX 2,000 USD per year,
Full Tuition Exemption.Sponsorship Awards from PKSHA Technology and HAKUHODO Technologies (1/140=0.7%)
The 18th Symposium of Young Researcher Association for NLP Studies (YANS 2023), 2023.Tokyo Tech Advanced Human Resource Development Fellowship for Doctoral Students
Tokyo Institute of Technology, 2023-2024.
Scholarship: 1,800,000 JPY / APPROX 12,000 USD per year, Research Funds: 300,000 JPY / APPROX 2,000 USD per year,
Full Tuition Exemption.