Publications

International Conference (Peer-reviewed)

  1. Investigating Learner-Aware Design of LLM-Generated Educational Feedback

    Momoka Furuhashi, Kouta Nakayama, Noboru Kawai, Takashi Kodama, Saku Sugawara, and Kyosuke Takami.

    The 5th Asia-Pacific Chapter of the Association for Computational Linguistics & the 15th International Joint Conference on Natural Language Processing (AACL-IJCNLP2026 Findings), pp. --, November, 2026, Hengqin, China.

  2. How Well Can LLMs Simulate Real Learner Evaluations of Educational Feedback?

    Momoka Furuhashi, Kouta Nakayama, Takashi Kodama, Saku Sugawara, and Kyosuke Takami.

    The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP2026 Main), pp. --, October, 2026, Budapest, Hungary.

  3. Investigating Oddness Annotation Ambiguity in LLM-Generated Stories for Elementary School Kanji Learning

    Kento Yoshimura, Kouta Nakayama, Takashi Kodama, Momoka Furuhashi, and Kyousuke Takami.

    The 34th International Conference on Computers in Education (ICCE2026), pp. --, November, 2026, New Zealand, Aotearoa.

  4. Are Checklists Really Useful for Automatic Evaluation of Generative Tasks?

    Momoka Furuhashi, Kouta Nakayama, Takashi Kodama, and Saku Sugawara.

    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP2025 Main), pp. 10641--10664, November, 2025, Suzhou, China.

    PaperCodeProject

    We investigate whether checklists should be used for all questions or selectively, generate them using six methods, evaluate their effectiveness across eight model sizes, and identify checklist items that correlate with human evaluations.

  5. Batch-wise Convergent Pretraining: Step-by-Step Learning Inspired by Child Language Development

    Ko Yoshida, Daiki Shiono, Kai Sato, Toko Miura, Momoka Furuhashi, and Jun Suzuki.

    Proceedings of the First BabyLM Workshop (BabyLM Workshop), pp. 508--524, November, 2025, Suzhou, China.

    Paper

  6. Automatic feedback generation for short answer questions using answer diagnostic graphs

    Momoka Furuhashi, Hiroaki Funayama, Yuya Iwase, Yuichiroh Matsubayashi, Yoriko Isobe, Toru Nagahama, Saku Sugawara, and Kentaro Inui.

    The 16th annual International Conference on Education and New Learning Technologies (EDULEARN 2024), pp. 6706--6716, July, 2024, Majorca, Spain.

    Paper

Journal (Peer-reviewed)

  1. 答案診断グラフを用いた国語記述式問題のための論理構造に基づくフィードバック自動生成.

    古橋 萌々香, 舟山 弘晃, 松林 優一郎, 震明 万智, 磯部 順子, 石井 雄隆, 乾 健太郎.

    Journal of Natural Language Processing, pp. 240--282, March, 2026.

    Paper

Domestic Conference (Non-peer-reviewed)

  1. 小学校漢字学習におけるLLM生成物語の「違和感」の類型化とLLM間の比較.

    吉村 賢人, 高見 享佑, 古橋 萌々香, 中山 功太, 児玉 貴志.

    The 21th Symposium of Young Researcher Association for NLP Studies (YANS 2026), September, 2026, Sendai, Japan.

  2. LLM による教育的フィードバックの生成と評価．

    古橋 萌々香, 中山 功太, 児玉 貴志, 菅原 朔, 高見 享佑.

    The 32th Annual Meeting of the Association for Natural Language Processing, pp. 3325--3330, March, 2026

    Paper

  3. Are Checklists Really Useful for Automatic Evaluation of Generative Tasks?

    Momoka Furuhashi, Kouta Nakayama, Takashi Kodama, and Saku Sugawara.

    Japanese Symposium on Open Large Language Models, November, 2025, Tokyo, Japan.

  4. 類題を用いた教育的フィードバックの自動評価.

    古橋 萌々香, 中山 功太, 児玉 貴志, 菅原 朔.

    The 20th Symposium of Young Researcher Association for NLP Studies (YANS 2025), September, 2025, Hamamatsu, Japan.

  5. バッチ単位収束型事前学習：子どもの言語発達に着想を得た一歩ずつの学習.

    吉田 倖, 塩野 大輝, 佐藤 魁, 古橋 萌々香, 三浦 東子, 鈴木 潤.

    The 20th Symposium of Young Researcher Association for NLP Studies (YANS 2025), September, 2025, Hamamatsu, Japan.

  6. 生成系タスクの自動評価においてチェックリストの使用は有効なのか？

    古橋 萌々香, 中山 功太, 児玉 貴志, 菅原 朔.

    The 31th Annual Meeting of the Association for Natural Language Processing (NLP 2025), pp. 1968--1973, March, 2025, Nagasaki, Japan.

    Paper

  7. チェックリストを利用した生成系タスクの網羅的評価.

    古橋 萌々香, 中山 功太, 児玉 貴志, 菅原 朔, 関根 聡, 宮尾 祐介.

    The 19th Symposium of Young Researcher Association for NLP Studies (YANS 2024), September, 2024, Osaka, Japan.

  8. 答案診断グラフを用いた国語記述式答案へのフィードバックの生成．

    古橋萌々香, 舟山弘晃, 岩瀬裕哉, 松林優一郎, 磯部順子, 菅原朔, 乾健太郎.

    The 30th Annual Meeting of the Association for Natural Language Processing (NLP 2024), pp. 18--23, March, 2024, Kobe, Japan.

    Paper

  9. 次世代教育のための論理的思考力育成データセットの生成について.

    古橋萌々香,松林優一郎,磯部順子,舟山弘晃,乾健太郎.

    The 18th Symposium of Young Researcher Association for NLP Studies (YANS 2023), August, 2023, Tokyo, Japan.

Article

  1. Are Checklists Really Useful for Automatic Evaluation of Generative Tasks? に至る研究過程．

    古橋 萌々香.

    Journal of Natural Language Processing, pp. 376--381, March, 2026

    Paper