HUANG FAN
I am Fan Huang, a second-year Informatics Ph.D. student in Complex Networks and Systems at Indiana University Bloomington. I am now advised by Prof. Jisun An, Prof. Haewoon Kwak, and Prof. Nathan Ensmenger, and I am also working with Prof. Yong-Yeol Ahn on exciting research projects.
My current research interests mainly focus on investigating the human-AI alignment problems and challenges and tackling the LLMs' biases and limitations toward better social integration of AI models. I am working on areas including Natural Language Processing, Artificial Intelligence, Computational Social Science, etc.
Education
Ph.D. of Informatics, Indiana University Bloomington, Indiana, United States. 2023-now
Ph.D. of Computer Science, Singapore Management University, Singapore. 2022-2023
Master of Information Systems, Nanyang Technological University, Singapore. 2020-2022
Bachelor of Computer Science & Technology, Central South University, China. 2014-2018
Contact: Google Scholar / LinkedIn Page / X (former Twitter) Gmail [fhuang181@gmail.com]
Research Publications:
2024
Fan Huang, Haewoon Kwak, Jisun An. Token-Ensemble Text Generation: On Attacking the Automatic AI-Generated Text Detection. arXiv.
Fan Huang, Haewoon Kwak, Kunwoo Park, Jisun An. ChatGPT Rates Like Human: Towards a Better Alignment of Text Explanation Quality Assessments. LREC-COLING (accepted).
2023:
Shaoyi Liaw, Fan Huang, Fabricio Benevenuto, Haewoon Kwak, Jisun An. YouNICon: YouTube's CommuNIty of Conspiracy Videos. ICWSM Dataset.
Fan Huang, Haewoon Kwak, Jisun An. Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech. The Web Conference (short paper).
Fan Huang, Haewoon Kwak, Jisun An. Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate Speech. The Web Conference (short paper).
Before 2023:
Highlight Timestamp Detection Model for Comedy Videos via Multimodal Sentiment Analysis. arXiv.
(URL: https://arxiv.org/abs/2106.00451)
Network Activities Recognition and Analysis Based on Supervised Machine Learning Classification Methods Using J48 and Naïve Bayes Algorithm. arXiv.
Master Dissertation:
Public Opinion Trend Analysis on Nuclear Energy via Aspect-based Sentiment Analysis Methods. Nanyang Technological University, 2021.
Talk & Workshop
Oral presentation at MSLD 2024 (Ann Arbor, Michigan), on the paper 'ChatGPT Rates Like Human: Towards a Better Alignment of Text Explanation Quality Assessments'.
Talk 'Natural Language Explanation: From XAI to Human-AI Interaction,' 2023, YY Group, CNetS, Indiana University Bloomington.
Poster presentation at WWW 2023 (Austin, Texas) on the paper 'Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech' and paper 'Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate Speech'.
Participants of SICSS (Summer Institute of Computational Social Science), 2022, NUS, Singapore.
Co-organizer of Workshop "Introduction to NLP", @IEEE NTU Student Branch, OCT-2021, NTU, Singapore.
Public Service
WSDM 2022, sub-reviewer.
ISSI 2023, student volunteer.