Hi, I am 孙豪 (Hao Sun), a NLP researcher in . I got my master’s degree from the Department of Computer Science and Technology, Tsinghua University. I was affiliated in CoAI group and fortunately supervised by A/Prof. Minlie Huang. Before Tsinghua University, I got my bachelor’s degree in Shanghai Jiao Tong University in 2020.

My research interests include

• Large-scale LLM training (Data collection, scalable model architecture, training algorithms, etc.);
• Scaling laws and training dynamics of LLMs;
• Safety and social implications of LLMs (mainly during my master period)

Publications

Find a part of my article list on my google scholar

* means equal contribution

• Hao Sun, Zhexin Zhang, Fei Mi, Yasheng Wang, Wei Liu, Jianwei Cui, Bin Wang, Qun Liu, Minlie Huang MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Constructing Moral Discussions. In the Association for Computational Linguistics: ACL 2023

• Hao Sun*, Guangxuan Xu*, Jiawen Deng, Jiale Cheng, Chujie Zheng, Hao Zhou, Nanyun Peng, Xiaoyan Zhu, and Minlie Huang. 2022. On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark. In Findings of the Association for Computational Linguistics: ACL 2022, pages 3906–3923, Dublin, Ireland. Association for Computational Linguistics.

• Hao Sun*, Zhenru Lin*, Chujie Zheng, Siyang Liu, and Minlie Huang. 2021. PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Support. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1489–1503, Online. Association for Computational Linguistics.

• Jiale Cheng, Sahand Sabour, Hao Sun, Zhuang Chen, Minlie Huang PAL: Persona-Augmented Emotional Support Conversation Generation. In Findings of Association for Computational Linguistics: ACL 2023

• Yuxian Gu*, Jiaxin Wen*, Hao Sun*, Yi Song, Pei Ke, Chujie Zheng, Zheng Zhang, Jianzhu Yao, Xiaoyan Zhu, Jie Tang, Minlie Huang EVA2. 0: Investigating Open-domain Chinese Dialogue Systems With Large-scale Pre-training. Mach. Intell. Res. (2023).

• Jiawen Deng*, Jingyan Zhou*, Hao Sun, Fei Mi, and Minlie Huang. 2022. COLD: A Benchmark for Chinese Offensive Language Detection. In Empirical Methods in Natural Language Processing: EMNLP 2022.
• Zhexin Zhang, Jiale Cheng, Hao Sun, Jiawen Deng, Fei Mi, Yasheng Wang, Lifeng Shang, Minlie Huang. 2022. Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation. In Findings of Empirical Methods in Natural Language Processing: EMNLP 2022.

Preprint

• Hao Sun, Zhexin Zhang, Jiawen Deng, Jiale Cheng, Minlie Huang. Safety Assessment of Chinese Large Language Models. arXiv preprint arXiv:2304.10436.
• Jiawen Deng, Hao Sun*, Zhexin Zhang, Jiale Cheng, Minlie Huang Recent Advances towards Safe, Responsible, and Moral Dialogue Systems: A Survey. *arXiv preprint arXiv:2302.09270.

Social Services

• Teaching Assistant of Artificial Neural Network in Tsinghua University, 2021/2022, autumn.

• Reviewer in ACL/EMNLP 2022/23/24, ICLR/Neurips 2024

Awards

• Outstanding Graduate in Tsinghua University, 2023.

• Outstanding Master Thesis in Tsinghua University, 2023.

• Second prize of Autumn Scholarship for Graduate Students of Tsinghua University, 2022

• Second prize of Autumn Scholarship for Graduate Students of Tsinghua University, 2021

• Second prize of Tencent Games Security Technology Competition (Track: Natural Language Processing), 2021

• Excellence award of Tencent Games Security Technology Competition (Track: Machine Learning), 2019