PPaperPicks

Naoaki Okazaki

12 papers at tracked venues · 5 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

ACL ×4EMNLP ×4NAACL ×2AAAI ×1ECAI ×1

Frequent coauthors

Masahiro Kaneko
×7
Ryuto Koike
×4
Youmi Ma
×2
Issa Sugiura
×2
Shuhei Kurita
×2
Daisuke Kawahara
×2
Mengsay Loem
×2
Ayana Niwa
×1
Preslav Nakov
×1
Keito Sasagawa
×1
Koki Maeda
×1
Yusuke Oda
×1

Papers

  1. ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability
    ACL 2026 ·
    Ryuto Koike
    ,
    Masahiro Kaneko
    ,
    Ayana Niwa
    ,
    Preslav Nakov
    , Naoaki Okazaki
  2. From Interpretability to Performance: Optimizing Retrieval Heads for Long-Context Language Models
    ACL 2026 ·
    Youmi Ma
    , Naoaki Okazaki
  3. Constructing Multimodal Datasets from Scratch for Rapid Development of a Japanese Visual Language Model
    NAACL 2025 ·
    Keito Sasagawa
    ,
    Koki Maeda
    ,
    Issa Sugiura
    ,
    Shuhei Kurita
    , Naoaki Okazaki,
    Daisuke Kawahara
  4. Developing Japanese CLIP Models Leveraging an Open-weight LLM for Large-scale Dataset Translation
    NAACL 2025 ·
    Issa Sugiura
    ,
    Shuhei Kurita
    ,
    Yusuke Oda
    ,
    Daisuke Kawahara
    , Naoaki Okazaki
  5. HMoE: Heterogeneous Mixture of Experts for Language Modeling
    EMNLP 2025 ·
    An Wang
    ,
    Xingwu Sun
    ,
    Ruobing Xie
    ,
    Shuaipeng Li
    ,
    Jiaqi Zhu
    ,
    Zhen Yang
    ,
    Pinxue Zhao
    ,
    Weidong Han
    ,
    Zhanhui Kang
    ,
    Di Wang
    , Naoaki Okazaki,
    Cheng-Zhong Xu
  6. Sampling-based Pseudo-Likelihood for Membership Inference Attacks
    ACL 2025 ·
    Masahiro Kaneko
    ,
    Youmi Ma
    ,
    Yuki Wata
    , Naoaki Okazaki
  7. Social Bias Evaluation for Large Language Models Requires Prompt Variations
    EMNLP 2025 ·
    Rem Hida
    ,
    Masahiro Kaneko
    , Naoaki Okazaki
  8. Distributional Properties of Subword Regularization
    EMNLP 2024 ·
    Marco Cognetta
    ,
    Vilém Zouhar
    , Naoaki Okazaki
  9. How You Prompt Matters! Even Task-Oriented Constraints in Instructions Affect LLM-Generated Text Detection
    EMNLP 2024 ·
    Ryuto Koike
    ,
    Masahiro Kaneko
    , Naoaki Okazaki
  10. Likelihood-based Mitigation of Evaluation Bias in Large Language Models
    ACL 2024 ·
    Masanari Ohi
    ,
    Masahiro Kaneko
    ,
    Ryuto Koike
    ,
    Mengsay Loem
    , Naoaki Okazaki
  11. OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples
    AAAI 2024 ·
    Ryuto Koike
    ,
    Masahiro Kaneko
    , Naoaki Okazaki
  12. SAIE Framework: Support Alone Isn't Enough - Advancing LLM Training with Adversarial Remarks
    ECAI 2024 ·
    Mengsay Loem
    ,
    Masahiro Kaneko
    , Naoaki Okazaki