Scholar
Zhengyuan Liu
Google Scholar ID: tqzidGsAAAAJ
Institute for Infocomm Research (I2R) - A*STAR; IEEE Senior Member.
Citations & Impact
Citations
1,084
H-index
18
i10-index
27
Publications
20
Co-authors
5
list available
Publications
Resume (English only)
Academic Achievements
- - Publications:
- - “Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD” published in EMNLP 2025.
- - “CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation” published in EMNLP 2025.
- - “COGENT: A Curriculum-oriented Framework for Generating Grade-appropriate Educational Content” presented at BEA 2025.
- - “SingaKids: A Multilingual Multimodal Dialogic Tutor for Language Learning” presented at ACL 2025 (Oral).
- - “Reinforcing Compositional Retrieval: Retrieving Step-by-Step for Composing Informative Contexts” published in ACL 2025.
- - “Scaling Up Collaborative Dialogue Analysis: An AI-driven Approach to Understanding Dialogue Patterns in Computational Thinking Education” published in LAK 2025.
- - “CrossIn: An Efficient Instruction Tuning Approach for Cross-Lingual Knowledge Alignment” won the Best Paper Award at SumEval@COLING 2025.
- - “Learning planning-based reasoning by trajectories collection and process reward synthesizing” won the Outstanding Paper Award at EMNLP 2024.
- - “Personality-aware Student Simulation for Conversational Intelligent Tutoring Systems” presented at EMNLP 2024.
- - “Optimizing Code-Switching in Conversational Tutoring Systems: A Pedagogical Framework and Evaluation” presented at SIGDIAL 2024.
- - “CRAFT: Extracting and Tuning Cultural Instructions from the Wild” won the Best Paper Award at C3NLP@ACL2024.
- - “Scaffolding Language Learning via Multi-modal Tutoring Systems with Pedagogical Instructions” presented at IEEE CAI 2024.
- - “Joint Dialogue Topic Segmentation and Categorization: A Case Study on Clinical Spoken Conversations” won the Outstanding Paper Award at EMNLP 2023.
- - “Learning from Bootstrapping and Stepwise Reinforcement Reward: A Semi-Supervised Framework for Text Style Transfer” presented at NAACL 2022.
Research Experience
- - Asst. Head of the AI4EDU Programme
- - Tech Lead of Multimodal Generative AI Group
- - Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR), Singapore
Background
- - Research Interests: Multimodal and Multilingual Foundation Models, Generative AI for Education, Healthcare, and Life Science, Accessibility, Reliability, and Explainability for Human-Centered AI.
Miscellany
- - Personal Interests: Open to collaboration or internship applications (remote internships are also welcome). Reach out via email.
