About Me

I am a PhD student in NUS IDS&SoC work with Bryan Hooi, See Kiong Ng and Luu Anh Tuan(NTU). Previously I visisted UCL WI group and AI centre. Before that I worked as a R&D engineer in natural language processing working with Prof. Zhang Richong, affiliated with BDBC and Computer Science College in Beihang University. My current research interests lie in LLM applications on task-oriented dialogue system, reasoning and calibration capability of LLM, as well as the LLM-powered Agent. You can also find me in Google Scholar Personal Page

Experience

2017.07 - 2019.07 ｜Research Intern｜ Beihang University, Beijing Advanced Innovation Center for Big Data and Brain Computing
2019.07 - 2022.09 ｜R & D Engineer ｜ Beihang University, Beijing Advanced Innovation Center for Big Data and Brain Computing
2022.09 - 2023.04 ｜Visiting Researcher ｜ University College London, Web Intelligence Group(UCL AI Centre)
2023.01 - Current ｜PhD Student ｜ National University of Singapore, Institute of Data Science and School of Computing

Publications

Zhiyuan Hu, Chumin Liu, Xidong Feng, Yilun Zhao, See-Kiong Ng, Junxian He, Anh Tuan Luu, Bryan Hooi. Planning and Reasoning Can Guide Large Language Models in Making Decision Under Uncertainty.
Lin Xu^, Zhiyuan Hu^, Daquan Zhou, Hongyu Ren, Zhen Dong, Kurt Keutze, See-Kiong Ng, Jiashi Feng. MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Audaptabiulity, Ratiuonality and Cuollaboration. Paper *Equal Contribution
Zhiyuan Hu, Yue Feng, Yang Deng, Zekun Li, See-Kiong Ng, Anh Tuan Luu, Bryan Hooi. Enhancing Large Language Model Induced Task-Oriented Dialogue Systems Through Look-Forward Motivated Goals.
Zhiyuan Hu, Yue Feng, Anh Tuan Luu, Bryan Hooi, Aldo Lipani. Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System, CIKM 2023 Paper
Miao Xiong, Zhiyuan Hu, Xinyang Lu, Yifei Li, Jie Fu, Junxian He, Bryan Hooi. Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs. ICLR 2024 Paper
Fanghua Ye, Zhiyuan Hu, Emine Yilmaz. Modeling User Satisfaction Dynamics in Dialogue via Hawkes Process. ACL 2023 Paper
Zhiyuan Hu, Chumin Liu, Yue Feng. PoetryDiffusion: Towards Joint Semantic and Metrical Manipulation in Poetry Generation. AAAI 2024 Paper
Richong Zhang, Zhiyuan Hu, Hongyu Guo, and Yongyi Mao, Syntax Encoding with Application in Authorship Attribution, EMNLP 2018 Code Paper
Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Khoi Le, Zhiyuan Hu, Cong-Duy Nguyen, See Kiong Ng, Anh Tuan Luu. READ-PVLA: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in LowResource Video-Language Modeling. AAAI 2024 Paper
Richong Zhang, Samuel Mensah, Fanshuang Kong, Zhiyuan Hu, Yongyi Mao, and Xudong Liu, Pairwise Link Prediction Model for Out of Vocabulary Knowledge Base Entities, ACM TOIS 2020 Code Paper
Richong Zhang, X. Liu, X. Chen, Zhiyuan Hu, Zhaoqing Xu, and Yiyong Mao, “Generating Chinese Ci with Designated Metrical Structure, AAAI 2019 Code Paper
Fanshuang Kong, Richong Zhang, Hongyu Guo, Samuel Mensah, Zhiyuan Hu, and Yongyi Mao, A Neural Bag-of-Words Modelling Framework for Link Prediction in Knowledge Bases with Sparse Connectivity, WWW 2019 Code Paper

Projects and Platforms

Services

LDC(Linguistic data consortium) Administrator in Beihang University
Organizator of “AAAI-2019 and AAAI-2022 Chinese Seminar”
Reviewer: ACL22, AACL22, COLING22,ACL23, SIGIR23, KDD23, AACL23, EMNLP23
TA: CS4248 Natural Language Processing, CS5228 Knowledge Discovery and Data Mining

Honors

NUS President’s Graduate Fellowship (PGF)

Talks

The latest Development of Language Model, Beihang Unviersity, Feb 2023
MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Audaptabiulity, Ratiuonality and Cuollaboration, AgentX, Dec 2023
Techniques in Longtext Generation, Docnote, Dec, 2023