About Me

I am a Research Scientist at Megagon Labs in Mountain View, California. I hold a Ph.D. in Information Science and Technology from Osaka University. My research passion lies at the intersection of Natural Language Processing (NLP), Graph Neural Networks (GNNs), and Machine Learning.

Currently, I am focusing on making Large Language Models (LLMs) more reliable and capable through function calling, retrieval augmentation, and long-context understanding.

Research Interests

NLP & LLMs

  • Function Calling & Tool Use
  • Long-context Understanding
  • Retrieval-Augmented Generation (RAG)
  • Active Learning

Graph Processing

  • Graph Neural Networks (GNNs)
  • Synthetic Graph Generation
  • Attributed Graph Clustering

Social Network Analysis

  • Follower Prediction / Link Prediction
  • Analysis on Incomplete Networks

Graph Database

  • Language-aware Indexing
  • Query Languages

Experiences

2024.04 - Present

Research Scientist

Megagon Labs Inc., Mountain View, CA

2023.04 - 2024.03

Research Associate

Megagon Labs Inc., Mountain View, CA

2022.01 - 2022.04

Research Intern

Megagon Labs Inc., Mountain View, CA

Working on Low-budget active learning to reduce labeling costs.

2020.09 - 2020.10

Research Intern

Hotto Link Inc., Remote

Follower prediction with limited API calls.

2020.04 - 2023.03

Specially Appointed Researcher

Osaka University, Osaka, Japan

2019.04 - 2020.03

Sales Engineer

NTT Docomo, Inc., Tokyo, Japan

2018.10 - 2018.12

Guest Student

Eindhoven University of Technology, Netherlands

2017.09

Visiting Student

The Chinese University of Hong Kong, Hong Kong

Selected Publications

View Full Publication List →

Selected Works

Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function Calling
Seiji Maekawa, Jackson Hassell, Pouya Pezeshkpour, Tom Mitchell, Estevam Hruschka
arXiv preprint, Sep. 2025
Paper Code
Same Content, Different Representations: A Controlled Study for Table QA
Yue Zhang, Seiji Maekawa, Nikita Bhutani
arXiv preprint, Sep. 2025
Paper Code
The Rarity Blind Spot: A Framework for Evaluating Statistical Reasoning in LLMs
Seiji Maekawa, Hayate Iso, Nikita Bhutani
arXiv preprint, Aug. 2025
Paper Code
Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-k
Chihiro Taguchi, Seiji Maekawa, Nikita Bhutani
EMNLP 2025 (Oral)
Paper Code
Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data
Seiji Maekawa*, Hayate Iso*, Nikita Bhutani
ICLR 2025
Paper Code Data
From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization
Catarina G. Belem, Pouya Pezeskhpour, Hayate Iso, Seiji Maekawa, Nikita Bhutani, Estevam Hruschka
Findings of NAACL 2025
Paper
Retrieval Helps or Hurts? A Deeper Dive into the Efficacy of Retrieval Augmentation to Language Models
Seiji Maekawa, Hayate Iso, Sairam Gurajada, Nikita Bhutani
NAACL 2024 (Oral), acceptance rate: 23.2%
Paper Code Poster
Low-resource Interactive Active Labeling for Fine-tuning Language Models
Seiji Maekawa, Dan Zhang, Hannah Kim, Sajjadur Rahman, Estevam Hruschka
Findings of EMNLP 2022
Paper Code
Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNs
Seiji Maekawa, Koki Noda, Yuya Sasaki, Makoto Onizuka
NeurIPS 2022 (Datasets & Benchmarks)
Paper Code

Awards & Activities

Awards

  • Kasami Award [嵩賞] (Outstanding Young Researcher Award), 2026 [Link]
  • Student Presentation Award at DEIM 2019 [Link]
  • Student Award at I-Scover Contest, 2017 [Link]

Recent Talks

  • "Holistic Reasoning with Long-Context LMs", NLP Colloquium (May 2025) [link] [YouTube]
  • "Introduction to Graph Neural Networks (Tutorial)", DEIM 2023 [link] [YouTube]
  • Guest Speaker at Josho Radio (Feb 2023) [link] [YouTube]

Program Committee

  • 2026: ICLR
  • 2025: ICLR, ARR May & July
  • 2024: ARR April & October, ECML PKDD AI4HR & PES Workshop, EACL NLP4HR Workshop, SDM, TKDE
  • 2023: IEEE BigData, CIKM, ACL Matching Workshop, KDD
  • 2022: NeurIPS D&B, ECML PKDD

Education

Ph.D. in Information Science and Technology

Osaka University / 2020-2023

MS in Information Science and Technology

Osaka University / 2017-2019

BE in Informatics

Kyoto University / 2012-2016

Technical Skills

Python (PyTorch, sklearn, NumPy) LLMs (RAG, Agents) Graph Neural Networks C++ SQL Git Docker