Project Researcher at NII.
My research focuses on understanding how LLMs acquire knowledge from training data, interpret it internally, and leverage it for reasoning.
My CV is here (last updated: Nov. 2, 2026).

• 2026/10 I have resigned from MBZUAI! Thank you to everyone I worked with there.
• 2026/10 We released two arxiv papers! Tracing How Language Models Integrate Temporal Anchors into Factual Recall and Rethinking the Evaluation of LLM Fact-Checkers.
• 2026/09 Our paper "Mitigating the Impact of Glitch Tokens via Targeted Retokenization" has been accepted at AACL 2026 Main 🎉
• 2026/08 We released JSFactCheckBench, Japanese fact-checking dataset on Huggingface Dataset!🤗 The paper will be available soon!
• 2026/07 I was recognized as a great reviewer at ACL 2026. 🎉
• 2026/07 We presented two papers at ACL 2026. 🗣️

Journal (Refereed)

• Nearest Neighbor Non-autoregressive Text Generation Journal of Information Processing, 2023 J-STAGE
  Ayana Niwa, Sho Takase, Naoaki Okazaki
• Construction of a Corpus of Rhetorical Devices in Slogans and Structural Analysis of Antitheses ACM TALLIP, 2021 ACM
  Ayana Niwa, Naoaki Okazaki, Kohei Wakimoto, Keisuke Nishiguchi, Masataka Mouri

International Conference (Refereed)

• Mitigating the Impact of Glitch Tokens via Targeted Retokenization AACL 2026
  Dmitrii Kuzmin, Carlos Javier Galán Zavala, Muhammad Alif Al Hakim, Tatsuya Hiraoka, Munachiso Samuel Nwadike, Ayana Niwa, Marco Cognetta, David Pohl, Kentaro Inui
• Disentangling the Effects of Unlearning in Measuring Parametric Faithfulness of Chain-of-Thought ACL 2026 SRW Anthology
  Ryo Mitsuhashi, Gaku Morio, Ayana Niwa, Masahiro Kaneko, Kentaro Inui, Terufumi Morishita, Yuta Koreeda, Yasuhiro Sogawa
• ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability ACL 2026 Findings Anthology
  Ryuto Koike, Masahiro Kaneko, Ayana Niwa, Preslav Nakov, Naoaki Okazaki
• JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks ICLR 2026 Arxiv
  Masahiro Kaneko, Ayana Niwa, Timothy Baldwin
• Rectifying Belief Space via Unlearning to Harness LLMs' Reasoning ACL 2025 Findings Anthology Poster
  Ayana Niwa, Masahiro Kaneko, Kentaro Inui
• AmbigNLG: Addressing Task Ambiguity in Instruction for NLG EMNLP 2024Anthology
  Ayana Niwa, Hayate Iso
• Interpretability for Language Learners Using Example-Based GEC ACL 2022 Anthology
  Masahiro Kaneko, Sho Takase, Ayana Niwa, Naoaki Okazaki
• Predicting Antonyms in Context using BERT INLG 2021 Anthology
  Ayana Niwa, Keisuke Nishiguchi, Naoaki Okazaki

Article / Preprint

• Tracing How Language Models Integrate Temporal Anchors into Factual Recall Arxiv, 2026 Arxiv
  Ayana Niwa, Masahiro Kaneko, Kentaro Inui
• Rethinking the Evaluation of LLM Fact-Checkers Arxiv, 2026Arxiv
  Ayana Niwa, Miyu Yamada, Kouta Nakayama, Masahiro Kaneko, Hisami Suzuki, Satoshi Sekine
• NLP Colloquium🚀 Journal of Natural Language Processing, 2024 J-STAGE
  Ayana Niwa, Sho Yokoi, Junya Takayama, Itsumi Saito
• JUBAKU: An Adversarial Benchmark for Exposing Culturally Grounded Stereotypes in Japanese LLMs Arxiv, 2026Arxiv
  Taihei Shiotani, Masahiro Kaneko, Ayana Niwa, Yuki Maruyama, Daisuke Oba, Masanari Ohi, Naoaki Okazaki

• "Language and AI: The World of NLP Research and Expanding Career Opportunities", Lecturer Keio University, 2026/06 InfoSlide
• “The Realities of Next-Generation AI Research and Careers: Emerging Opportunities Between Japan and the UAE”, Panelist The Asahi Shimbun Middle East, 2025/12 Info Article 1Article 2
• “Candid Talks by Young Tokyo Tech Alumni — AI Industry Edition”, PanelistKuramae Alumni Association, 2025/11, Youtube (To appear)
• “A Quick Overview to Unlock the Potential of LLMs through Prompt Engineering.” Tokyo AI, 2024/08 Slides
• “The Frontiers of Mathematics, Information, and AI.” RIKEN AIP, 2022/11 YouTube
• “Career Path as a Female Researcher.” NeurIPS Meetup Japan WiML, 2021/12
• “Derivation and Use of Templates in NLG.”SIG‑FPAI, 2021/11 Info
• “Trends in NLP at NeurIPS 2019.”JSAI AI Seminar, 2020/03 Slides
• “A Smart Computer that Understands Language.”A visiting lecture at Jissen Gakuen Senior High School, 2019/11
• “Natural Language Processing.”A visiting lecture at Denenchofu High School, 2019/06

• SIG‑NL Committee (2025/04 –)
• ANLP Editorial Committee (2025/04 –)
• JSAI Planning Committee (2024/05 –)
• INLG 2024 Sponsor Chair (2024)
• NLP 2024 Executive Committee (2024)
• ACL 2023 Visa Assistance Team (2023)
• NLP Colloquium Organizer (2021/06 – ) • X • YouTube
• NLP Study Group for Doctoral Students Organizer (2020/12 - 2023/03)
• Young Researcher Association for NLP Studies (YANS) Committee (2020/03 - 2022/03)

Scholarships & Grants

• JSPS Research Fellowship (DC2) 4.8M JPY/yr (2021–2023) [Acceptance Rate < 20%]
• JSPS Fellows Grant (21J13602) 1.5M JPY (2021–2023)
• NeurIPS 2019 travel & registration supportJSAI
• Tokyo Tech Tsubame Scholarship480k JPY/yr (2020–2021)

Awards and Honors

• Great Reviewer (133/8594) ACL 2026Page
• Committee Special Award (32/748) NLP 2026Page (Ja)
• JSAI Annual Conference Award (as first-author) (16/513) JSAI 2025Page (Ja)
• JSAI Annual Conference Award (as co-author) (16/513) JSAI 2025Page (Ja)
• Young Researcher’s Encouragement Award (18/427) NLP 2024Page (Ja)
• Committee Special Award (16/365) NLP 2022Page (Ja)
• Nomination Award (17/157) 2021 Microsoft Research Asia FellowshipPage

Teaching & Mentoring

• Mentor, UGRIP program, MBZUAI (2025)two mentee projects; one Best Presentation Award🎉
• TA, Machine Learning, Tokyo Tech 2020 4Q, 2021 4Q