avatar

Chuyuan Li

Postdoc Researcher
University of British Columbia
chuyuan.li (at) ubc.ca


About Me

Welcome! I am Chuyuan 李楚源. Usually, I go by Lisa.

I recently joined Université Grenoble Alpes as a postdoc researcher, working on efficient training of large multimodal and specialized French language models as part of the PARTAGES project. Previouly, I worked with Giuseppe Carenini at the University of British Columbia in Canada. I obtained my Ph.D. at Lorraine Research Laboratory in Computer Science and its Applications (LORIA) and Université de Lorraine (UL). During my Ph.D. years, I was fortunately advised by Maxime Amblard and Chloé Braud. Prior to that, I earned my Master’s in Computational Linguistics from Université Paris Cité (formerly Paris 7).

Research Interests

I have broad interests in natural language processing and computational linguistics. Some of the topics that I am currently researching include:

News

Publications

  1. EACL
    BeDiscovER: The Benchmark of Discourse Understanding in the Era of Reasoning Language Models
    Chuyuan Li, Giuseppe Carenini
    European Chapter of the Association for Computational Linguistics (EACL), 2026.
    PDF Code Slides

  2. Findings EMNLP
    Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarization
    Chuyuan Li, Austin Xu, Shafiq Joty, Giuseppe Carenini
    Findings of the Empirical Methods in Natural Language Processing (Findings EMNLP), 2025.
    PDF Code Poster

  3. EMNLP
    CEMTM: Contextual Embedding-based Multimodal Topic Modeling
    Amirhossein Abaskohi, Raymond Li, Chuyuan Li, Shafiq Joty, and Giuseppe Carenini
    Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025.
    PDF

  4. ACL
    Delta-KNN: Improving Demonstration Selection in In-Context Learning for Alzheimer's Disease Detection
    Chuyuan Li, Raymond Li, Thalia S. Field, and Giuseppe Carenini
    Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025.
    PDF Code Poster Slides

  5. Findings ACL
    Explicit Bayesian Inference to Uncover the Latent Themes of Large Language Models
    Raymond Li, Chuyuan Li, Gabriel Murray, and Giuseppe Carenini
    Findings of the Association for Computational Linguistics (Findings ACL), 2025.
    PDF Poster

  6. On Large Foundation Models and Alzheimer's Disease Detection
    Chuyuan Li, Giuseppe Carenini, Thalia S. Field
    Proceedings of the Second Workshop on Patient-Oriented Language Processing (CL4Health), NAACL, 2025.
    PDF Poster

  7. Multimodal Classification of Alzheimer's Disease by Combining Facial and Eye-tracking Data
    Shih-Han Chou, Miini Teng, Harshinee Sriram, Chuyuan Li, Giuseppe Carenini, Cristina Conati, Thalia S. Field, Hyeju Jang, Gabriel Murray
    Proceedings of the 4th Machine Learning for Health Symposium (CL4H), PMLR, 2024.
    PDF Slides

  8. Dialogue Discourse Parsing as Generation: a Sequence-to-Sequence LLM-based Approach
    Chuyuan Li, Yuwei Yin, and Giuseppe Carenini
    Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGdial), 2024.
    PDF Code Slides Best Paper Award

  9. Coherence-based Dialogue Discourse Structure Extraction using Open-Source Large Language Models
    Gaetano Cimino, Chuyuan Li, Giuseppe Carenini, and Vincenzo Deufemia
    Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGdial), 2024.
    PDF

  10. Discourse Relation Prediction and Discourse Parsing in Dialogues with Minimal Supervision
    Chuyuan Li, Chloé Braud, Maxime Amblard, and Giuseppe Carenini.
    Proceedings of the 5th Workshop on Computational Approaches to Discourse (CODI), 2024.
    PDF Poster

  11. Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialogues
    Chuyuan Li, Patrick Huber, Wen Xiao, Maxime Amblard, Chloé Braud and Giuseppe Carenini.
    Findings of the European Chapter of the Association for Computational Linguistics (Findings EACL), 2023.
    PDF Code Slides

  12. Multi-Task Learning for Depression Detection in Dialogs
    Chuyuan Li, Chloé Braud, and Maxime Amblard
    Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGdial), 2022.
    PDF Code Poster

  13. Investigation par méthodes d’apprentissage des spécificités langagières propres aux personnes avec schizophrénie (Investigating Learning Methods Applied to Language Specificity of Persons with Schizophrenia).
    Maxime Amblard, Chloé Braud, Chuyuan Li, Michel Musiol, Caroline Demily et Nicolas Franck.
    Actes de la 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition) (JEP-TALN-RÉCITAL), 2020.
    PDF Slides

Services

Co-Organizer

Program Committee/Reviewer


Powered by Jekyll and Minimal Light theme.