Junfeng JIANG

Junfeng JIANG

⬆️Are they cute?⬆️

This is Junfeng JIANG (江俊锋，こう　しゅんほう). Currently, I am a D3 student at the University of Tokyo under the supervision of Prof. Akiko Aizawa, supported by SPRING GX Program.

My research direction is focusing on developing biomedical large language models. My previous research direction is Document-grounded Dialogue System (DGDS). Unfortunately, it was almost perfectly done by CloseAI’s ChatGPT/GPT-4. As a human, it is a piece of good news but as for a PhD candidate, it sucks. Anyway, any interesting discussion is welcome and my full publications can be accessed from Google Scholar.).

Currently, I am working on research related to

  • Large Language Model (not so large but large enough that cannot be fitted in a single A100 80GB GPU)
  • Biomedical Language Model
  • Dialogue Segmentation
  • Chain-of-thought Finetuning

Any collaboration or discussion is welcome!

🔥 News

  • 2024.09: 💪🏻 Details of JMedBench have been released in this paper.
  • 2024.09: 🎉 A paper was accepted as the EMNLP 2024 findings.
  • 2024.09: 💪🏻 JMedBench is publicly available to support the development of Japanese biomedical LLMs.
  • 2024.01: 💪🏻 A survey paper for SciLMs has been completed.
  • 2023.08: BioMed-Llama is publicly available.

📖 Educations

  • 2022.04 - Now, Ph.D. candidate in Computer Science, The University of Tokyo.
  • 2019.09 - 2022.04, M.S. in Computer Science (2.88/3.0), The University of Tokyo.
  • 2015.08 - 2019.07, B.S. in Mathematics And Applied Mathematics (3.7/5.0), Sun Yat-Sen University.

📝 Publications

Journals

  • Detai Xin*, Junfeng Jiang*, Shinnosuke Takamichi, Yuki Saito, Akiko Aizawa, & Hiroshi Saruwatari. (2024). JVNV: A Corpus of Japanese Emotional Speech with Verbal Content and Nonverbal Expressions, in IEEE Access, vol. 12, pp. 19752-19764, 2024, doi: 10.1109/ACCESS.2024.3360885.

Conference Papers

  • Junfeng Jiang, Fei Cheng, Akiko Aizawa. Improving Referring Ability for Biomedical Language Models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Miami, Florida, U.S.A. Association for Computational Linguistics. (EMNLP 2024, findings). [paper]; [code].
  • Davide Baldelli, Junfeng Jiang, Akiko Aizawa and Paolo Torroni. TWOLAR: a TWO-step LLM-Augmented distillation method for passage Reranking. In European Conference on Information Retrieval, vol 14608, pages 470-485, 2024, Springer. doi: 10.1007/978-3-031-56027-9_29. (ECIR 2024). [paper]; [code].
  • Junfeng Jiang, Chengzhang Dong, Sadao Kurohashi, Akiko Aizawa. SuperDialseg: A Large-scale Dataset for Supervised Dialogue Segmentation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 4086–4101, Singapore. Association for Computational Linguistics. (EMNLP 2023). [paper]; [code].
  • An Wang, Junfeng Jiang, Youmi Ma, Ao Liu, and Naoaki Okazaki. 2023. Generative Data Augmentation for Aspect Sentiment Quad Prediction. In Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023), pages 128–140, Toronto, Canada. Association for Computational Linguistics. (*SEM 2023). [paper]; [code].
  • Che Liu, Rui Wang, Junfeng Jiang, Yongbin Li, Fei Huang. Dial2vec: Self-Guided Contrastive Learning of Unsupervised Dialogue Embeddings. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7272–7282, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. (EMNLP 2022). [paper]; [code].
  • Junfeng Jiang*, An Wang*, and Akiko Aizawa. Attention-based Relational Graph Convolutional Network for Target-Oriented Opinion Words Extraction. The 16th Conference of the European Chapter of the Association for Computational Linguistics, pp.1986–1997. Online, April 19–23, 2021. (EACL 2021). [paper]; [code].
  • Che Liu, Junfeng Jiang, Chao Xiong, Yi Yang, Jieping Ye. Towards Building an Intelligent Chatbot for Customer Service: Learning to Respond at the Appropriate Time. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 3377-3385). (KDD 2020). [paper].

Preprints

  • Junfeng Jiang, Jiahao Huang, Akiko Aizawa. JMedBench: A Benchmark for Evaluating Japanese Biomedical Large Language Models. arXiv preprint arXiv:2409.13317. [paper]; [data].
  • Chengzhi Zhong, Fei Cheng, Qianying Liu, Junfeng Jiang, Zhen Wan, Chenhui Chu, Yugo Murawaki, & Sadao Kurohashi. Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?. arXiv preprint arXiv:2408.10811. [paper].
  • Xanh Ho*, Anh Khoa Duong Nguyen*, An Tuan Dao*, Junfeng Jiang*, Yuki Chida*, Kaito Sugimoto*, Huy Quoc To, Florian Boudin, Akiko Aizawa. A Survey of Pre-trained Language Models for Processing Scientific Text. arXiv preprint arXiv:2401.17824. [paper].
  • Chao Xiong, Che Liu, Zijun Xu, Junfeng Jiang, Jieping Ye. Sequential Sentence Matching Network for Multi-turn Response Selection in Retrieval-based Chatbots. arXiv preprint arXiv:2005.07923. [paper].
  • Junfeng Jiang, Jiahao Li. Constructing financial sentimental factors in Chinese market using natural language processing. arXiv preprint arXiv:1809.08390. [paper]; [code].

💻 Projects

💰 Fundings

  • 2022.12 - 2023.03, Self-directed and integrated project research, SPRING GX, JST. (~500K JPY)
  • 2022.04 - 2025.04, SPRING GX, JST. (~1M JPY)

👨‍💻 Internships

  • 2022.12 - Now, Research Assistant, National Institute of Informatics, Tokyo, Japan.
  • 2022.05 - 2022.09, NLP Research Intern, Alibaba DAMO Academy, Beijing, China.
  • 2020.12 - 2021.05, NLP Research Intern, Baidu Inc., Shenzhen, China.
  • 2020.08 - 2020.12, NLP R&D Intern, Tencent Inc., Shenzhen, China.
  • 2019.10 - 2020.08, NLP Research Intern, Didi Chuxing AI Labs, Beijing, China.
  • 2018.07 - 2019.01, AI Research Intern, Likelihood Lab, Guangzhou, China.

👓 Committees

  • Invited Reviewer for conferences: COLING 2025; CIKM 2024; LREC-COLING 2024; ACL 2023; EACL 2023; EMNLP 2023,2022,2021.
  • Secondary Reviewer for conferences: IJCNLP-AACL 2023.