Rikiya Takehi

PhD Student at MIT CSAIL

Rikiya Takehi

I am interested in Machine Learning (ML), Natural Language Processing (NLP), and Information Retrieval (IR). Now, I am especially interested in designing better LLMs / LLM Systems / LLM Agents.

I am a first-year PhD student at MIT CSAIL, advised by Prof. Omar Khattab. I recently received a B.Eng. from Waseda University, where I was supervised by Prof. Tetsuya Sakai. Previously, I was a research intern at NVIDIA Research, focusing on AI agents. Before that, I was a guest researcher at NIST working with Dr. Ian Soboroff and Dr. Ellen Voorhees, and I have also collaborated with Prof. Fernando Diaz of CMU LTI on retrieval rankings.

My first two years of graduate studies are funded by the Toyota PhD Fellowship.

CV| Email| Twitter| Google Scholar| Github

News

scroll ↓
  • Mar.2026: Graduated from Waseda University as the representative recipient of the Ono Azusa Award, Waseda University's highest honour award, selected as 1 student out of 10,000+ science and engineering students including graduate students (top 0.01%).
  • Mar.2026: Started a research internship at NVIDIA Research, focusing on AI agents.
  • Feb.2026: First-authored full paper Diversification as Risk Minimization received the WSDM 2026 Best Paper Award.
  • Feb.2026: Our Hugging Face ColBERT models mxbai-edge-colbert-v0-17m and mxbai-edge-colbert-v0-32m surpassed 3M+ downloads in total.
  • Jan.2026: Co-first-authored full paper Retention-Driven Two-Sided Matching got accepted to ICLR 2026.
  • Oct.2025: First authored full paper Diversity as Risk Minimization got accepted to WSDM 2026.
  • Oct.2025: Released two open-source ColBERT models mxbai-edge-colbert-v0-17m and mxbai-edge-colbert-v0-32m. Tech report here.
  • Aug.2025: My co-authored paper got accepted to CIKM 2025.
  • Aug.2025: Started research internship at Mixedbread.
  • Jul.2025: Selected as a Toyota PhD Fellow: 2 yrs of full funding.
  • Jul.2025: Gave an invited talk (w/ Prof. ChengXiang Zhai) at SIGIR 2025 eCOM Workshop invited by Dr. Tracy Holloway King.
  • Jun.2025: Invited as a panelist at NTCIR 2025 with Prof. Maarten De Rijke, Prof. Mark Sanderson, Prof. Charles Clarke, & Prof. Ian Soboroff.
  • Jun.2025: Gave an invited talk at EVIA 2025 about Using LLMs as Assistants for Building Test Collections invited by Prof. Charles Clarke, Prof. Noriko Kando, & Prof. Makoto Kato. Slides can be found here.
  • Apr.2025: First authored full paper LLM-Assisted Relevance Assessments: When Should We Ask LLMs for Help? got accepted to SIGIR 2025!!
  • Jan.2025: First authored full paper General Framework for Off-Policy Learning with Partially-Observed Reward got accepted to ICLR 2025.
  • Nov.2024: Gave an invited talk at NII about Using LLMs as Assistants for Building Test Collections invited by Prof. Noriko Kando.
  • Nov.2024: First authored paper LLM-Assisted Relevance Assessments: When Should We Ask LLMs for Help? preprint available on arXiv.
  • Oct.2024: Started research internship at CyberAgent AI Lab. Algorithm Team.
  • Aug.2024: Gave an invited talk at UMD College Park about Nugget-Based Evaluation and the Use of LLMs invited by Prof. Douglas Oard.
  • Oct.2023: First-authored paper Open-Domain Dialogue Quality Evaluation: Deriving Nugget-level Scores from Turn-level Scores accepted to SIGIR AP 2023.

Publications

You can also find my articles on my Google Scholar profile.

  1. Diversification as Risk Minimization
    Rikiya Takehi, Fernando Diaz, Tetsuya Sakai. 2025.
    WSDM 2026.
    Best Paper Award (top 0.1%, 1 of 799 submissions)
    arXiv
  2. Beyond Match Maximization and Fairness: Retention-Objectified Two-Sided Matching
    Rikiya Takehi*, Ren Kishimoto*, Koichi Tanaka, Masahiro Nomura, Riku Togashi, Yuta Saito. 2025.
    ICLR 2026.
    preprint
  3. Fantastic (small) Retrievers and How to Train Them: mxbai-edge-colbert-v0 Tech Report.
    Rikiya Takehi, Benjamin Clavié, Sean Lee, Aamir Shakir. 2025.
    Tech Report.
    3M+ downloads on Hugging Face
    Tech Report | Blog | 17M ColBERT model | 32M ColBERT model
  4. General Framework for Off-Policy Learning with Partially-Observed Reward
    Rikiya Takehi, Kosuke Kawakami, Masahiro Asami, Yuta Saito. 2025.
    ICLR 2025.
    arXiv | OpenReview | presentation | poster
  5. LLM-Assisted Relevance Assessments: When Should We Ask LLMs for Help?
    Rikiya Takehi, Ellen M. Voorhees, Tetsuya Sakai, and Ian Soboroff. 2025.
    SIGIR 2025.
    arXiv | slides | code
  6. Open-Source LLM-based Relevance Assessment vs. Highly Reliable Manual Relevance Assessment: A Case Study
    Tetsuya Sakai, Khant Myoe Rain, Rikiya Takehi, Sijie Tao, Youngin Song. 2025.
    CIKM 2025.
    proceedings
  7. Objective-driven Calibrated Recommendations
    Rikiya Takehi*, Koichi Tanaka*, Ren Kishimoto, Masahiro Nomura, Riku Togashi, Yuta Saito. 2025.
    preprint
  8. Open-Domain Dialogue Quality Evaluation: Deriving Nugget-level Scores from Turn-level Scores
    Rikiya Takehi, Akihisa Watanabe, and Tetsuya Sakai. 2023.
    SIGIR-AP 2023.
    code | poster | slides | proceedings

Experience

  • Mar 2026 - Aug 2026 · remote
    Research Intern, NVIDIA Research
  • Aug 2025 - Feb 2026 · CA, USA
    Research Intern, Mixedbread
  • Oct 2024 - Sep 2025 · Tokyo, Japan
    Research Intern, CyberAgent AI Lab. Algorithm Team
  • Sept 2024 - Apr 2025 · Tokyo, Japan
    Research Intern, Hakuhodo Tech Inc.
  • Oct 2023 - Sep 2024 · Maryland, US
    Guest Researcher, NIST Retrieval Group

Achievements

2026–2027 · MIT
MIT Distinguished Science and Engineering Fellowship

Awarded to PhD students with exemplary academic and research achievements and great promise for future accomplishments.

Mar 2026 · Waseda University
Waseda University Highest Honour Award

Graduated as the representative recipient of the Ono Azusa Award, selected as 1 student out of 10,000+ science and engineering students including graduate students (top 0.01%).

Feb 2026 · WSDM 2026
WSDM 2026 Best Full Research Paper Award

Diversification as Risk Minimization received the Best Paper Award (1 of 799 submissions).

Jul 2025 · Toyota PhD Fellowship
Toyota PhD Fellowship

Selected as a Toyota PhD Fellow, with my first two years of graduate studies fully funded.

Selected Invited Talks

  • Feb 2026 · Invited by Dr. Thorsten Joachims (Cornell)
    Cornell University
    Diversification as Risk Minimization
  • Jul 2025 · Invited by Dr. Tracy Holloway King (Adobe)
    SIGIR eCom Workshop 2025
    Product Search and Recommendations (with Prof. ChengXiang Zhai)
  • Jun 2025 · Invited by Prof. Charles Clarke (UWaterloo)
    EVIA 2025
    Using LLMs as Assistants for Building Large Test Collections
  • Aug 2024 · Invited by Prof. Douglas Oard (UMD)
    University of Maryland, College Park
    Nugget-Based Evaluation and the Use of LLMs
  • 2025 · Panel
    NTCIR 2025 Panelist
    With Profs. Maarten de Rijke (UvA), Mark Sanderson (RMIT), Charles Clarke (UWaterloo), and Ian Soboroff (NIST).