Yuhan Liu
刘禹菡
Senior,Xi'an Jiaotong University
lyh6560 [AT] stu.xjtu.edu.cn
Bio
Hi! I am currently a senior undergraduate at Xi'an Jiaotong University.(curriculum vitae).
I am also the director of the LUD lab.
I am mostly interested in NLP for social good, social network analysis, and knowledge graph representation learning. A few topics of recent interest are,
- LLMs for the Greater Good
- Large language models are inherently biased and can exert an unfair impact on downstream tasks. How can we measure and mitigate the bias in the generated texts?
- Bot detection on social platform(MoE)
- Malicous bots are posing threats to the social environment and are continuing to evade detection with the aid of automatic programs forging metadata, forged or stolen tweets, Botnets etc. How can we jointly leverage user information of multi-modalities ( textual features, structured user metadata, social network structure and so on) for bot detection?
News
From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models
Shangbin Feng, Chan Young Park, Yuhan Liu, Yulia Tsvetkov
ACL 2023
We propose to study the political bias propagation pipeline from pretraining data to language models to downstream tasks. We find that language models do have political biases, such biases are in part picked up from pretraining corpora, and they could result in fairness issues in LM-based solutions to downstream tasks.
BotMoE: Twitter Bot Detection with Community-Aware Mixtures of Modal-Specific Experts
Yuhan Liu, Zhaoxuan Tan, Heng Wang, Shangbin Feng, Qinghua Zheng, Minnan Luo
SIGIR 2023
We propose community-aware mixture-of-experts to address two challenges in detecting advanced Twitter bots: manipulated features and diverse communities.
Publications
Most recent publications on Google Scholar.
BotMoE: Twitter Bot Detection with Community-Aware Mixtures of Modal-Specific Experts
Yuhan Liu, Zhaoxuan Tan, Heng Wang, Shangbin Feng, Qinghua Zheng, Minnan Luo
In Proceedings of SIGIR, 2023
TwiBot-22: Towards Graph-Based Twitter Bot Detection PDF
Shangbin Feng, ... , Yuhan Liu, ... , Minnan Luo
In Proceedings of the NeurIPS, Datasets and Benchmarks Track, 2022
BotMoE: Twitter Bot Detection with Community-Aware Mixtures of Modal-Specific Experts
Yuhan Liu, Zhaoxuan Tan, Heng Wang, Shangbin Feng, Qinghua Zheng, Minnan Luo
In Proceedings of SIGIR, 2023
TwiBot-22: Towards Graph-Based Twitter Bot Detection PDF
Shangbin Feng, ... , Yuhan Liu, ... , Minnan Luo
In Proceedings of the NeurIPS, Datasets and Benchmarks Track, 2022
Resume
-
XLang Lab, HKU NLP 2023 - nowResearch Assistant, advised by Prof.Tao Yu from The University of Hong Kong
Personalized language models -
TsvetShop, UW 2023 - nowResearch Assistant, advised by Prof.Yulia Tsvetkov from the University of Washington
Personalized language models -
Luo Lab Undergraduate Division 2022 - nowDirector, Research Assistant, advised by Prof.Minnan Luo
Natural language processing, graph representation learning, Twitter bot detection -
National Scholarship 2022The highest honor for undergraduates in China
-
Reviewer for NeurIPS 2022Datasets and Benchmarks Track
-
XJTU-VTOL 2021-2022Vice President
Multi-object tracking, attending robot advanced vision track of CHINA ROBOT COMPETITION -
National Scholarship 2021The highest honor for undergraduates in China
-
Xi'an Jiaotong University 2020 - 2024Undergraduate in Engineering Experimental Class (Qian Xuesen Class H)
Double major in EE and Informatics, rank 1st/23 -
The Chinese Mathematics Competitions 2020First Prize
At the age of 17 -
Xi'an Jiaotong University(member of the C9 league in China) 2018 - 2019The Special Class for the Gifted Young / Honors Youth Program
entering college at the age of 15, rank 2nd/116
Acknowledgement
This website uses the website design and template by Martin Saveski