Rikiya Takehi

Rikiya Takehi

third-year B.A. student at Waseda University

About Me

I am Rikiya Takehi (武樋力哉), a fourth-year undergraduate student at Waseda University, where I am honored to be supervised by Prof. Tetsuya Sakai.
Previously, I was a guest researcher at NIST in the US for one year, working with Dr. Ian Soboroff and Dr. Ellen Voorhees, conducting research mainly on evaluation.
I also collaborate closely with Yuta Saito of Cornell Univ., working on counterfactual learning and fairness in rankings.

I am co-organizing Product Search and Recommendations Track at TREC (previously Product Search Track).

My research widely orbits around information retrieval and machine learning, particularly evaluation, counterfactual learning, and recommendation.

News

  • 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 paper LLM-Assisted Relevance Assessments: When Should We Ask LLMs for Help? got accepted to SIGIR 2025!!
  • Jan.2025: First authored 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.

Experience