Research

研究

  • Home
  • 研究業績
  • LLM / NLP

    • 研究業績

    カテゴリー

    研究領域

    年

    • 国際会議
      LLM / NLP 応用研究

      Training-Free Residual-Guided Retrieval for Multi-hop KGQA with Single-Step LLM Inference

      Keito Sei, Sunil Kumar Maurya, Yohei Kobashi, Yutaka Matsuo

      Proceedings of the 5th Asia-Pacific Chapter of the Association for Computational Linguistics and the 15th International Joint Conference on Natural Language Processing (AACL-IJCNLP 2026), Main, November 2026

    • 国際会議
      LLM / NLP

      From Chains to Graphs: Self-Structured Reasoning for General-Domain LLMs

      Yingjian Chen, Haoran Liu, Yinhong Liu, Sherry T. Tong, Aosong Feng, Jinghui Lu, Juntao Zhang, Yusuke Iwasawa, Yutaka Matsuo, Irene Li

      Proceedings of the 5th Asia-Pacific Chapter of the Association for Computational Linguistics and the 15th International Joint Conference on Natural Language Processing (AACL-IJCNLP 2026), Findings, November 2026

    • 国際会議
      LLM / NLP 応用研究 機械学習一般

      Lightweight Ban Prediction in YouTube Live-Stream Chat: Per-Genre Feature Selection and Automatic Genre Assignment

      Ryotaro Hamada, Yohei Kobashi, Hiroto Sudo, Yutaka Matsuo

      Proceedings of the 25th IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT 2026), Regular Paper, December 2026

    • 国際会議
      LLM / NLP

      Training Lightweight PII Text Detectors via Rubric-Guided Contrastive Data Synthesis

      [paper]

      Shota Ekuni, Jie Zeng, Yohei Kobashi, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

      Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026), Industry Track, October 2026

    • 国際会議
      LLM / NLP

      In-Context Neurofeedback: Can LLMs Control Their Internal Representations through Privileged Access?

      [paper]

      Koshiro Aoki, Ryota Takatsuki, Gouki Minegishi, Yusuke Haruki, Daisuke Kawahara

      Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026), Findings, October 2026

    • 国際会議
      LLM / NLP

      Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training

      [paper]

      Kohsei Matsutani, Gouki Minegishi, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

      Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026), Findings, October 2026

    • 国際会議
      LLM / NLP

      Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models

      [paper]

      Xiaojie Gu, Sherry T. Tong, Aosong Feng, Sophia Simeng Han, Jinghui Lu, Yingjian Chen, Yusuke Iwasawa, Yutaka Matsuo, Chanjun Park, Rex Ying, Irene Li

      Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026), Findings, October 2026

    • 国際会議
      LLM / NLP

      Batch-wise Adaptive Pruning: Periodic Neuron Activation-Aware Weight Pruning for Language Reasoning Model

      Yongmin Kim, Shota Takashiro, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

      Proceedings of the 3rd Conference on Language Modeling (COLM 2026), October 2026

    • 国際会議
      LLM / NLP 医療AI

      JMedEthicBench: A Multi-Turn Adversarial Benchmark for Japanese Medical Ethics Alignment in LLMs

      [paper]

      Junyu Liu, Zirui Li, Qian Niu, Zequn Zhang, Yue Xun, Wenlong Hou, Shujun Wang, Yusuke Iwasawa, Yutaka Matsuo, Kan Hatakeyama-Sato

      Proceedings of the 3rd Conference on Language Modeling (COLM 2026), October 2026

    • 国際会議
      LLM / NLP

      AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning

      [paper]

      Haoyu Zhang, Jiaxian Guo, Dong Yang, Yusuke Iwasawa, Yutaka Matsuo

      Annual Conference of the International Speech Communication Association (Interspeech 2026), September 2026