Current Position 当前职位
About Me 简介
I am currently a postdoctoral fellow at the College of Computer Science and Technology, Jilin University. My recent work asks how language models can generalize beyond brittle shortcuts, learn from better demonstrations, and serve humanities research on ancient Chinese scripts.
我目前为吉林大学 计算机科学与技术学院博士后。 近期研究关注语言模型如何摆脱脆弱捷径、从更优示例中学习，并服务于古文字等人文研究场景。
Academic Path 教育经历
Education 教育经历
Ph.D. in Artificial Intelligence 人工智能博士
School of Artificial Intelligence, Jilin University 吉林大学人工智能学院
Mentors: 导师： Prof. Fausto Giunchiglia Foreign Member of the Chinese Academy of Sciences; Member of Academia Europaea 中国科学院外籍院士、欧洲科学院院士 and 与 Prof. Hao Xu
M.S. in Computer Science and Technology 计算机科学与技术硕士
College of Computer Science and Technology, Jilin University 吉林大学计算机科学与技术学院
Mentor: 导师： Prof. Lan Huang
B.S. in Software Engineering 软件工程学士
School of Software Engineering, Jilin University 吉林大学软件学院
Recent Updates 最新动态
News 新闻
Selected Work 代表成果
Selected Publications 代表论文
* Corresponding author* 通讯作者
AI for Humanity: Culture人文智能：文化
3AI for Humanity: Social Bias人文智能：社会偏见
9Automatic Prompt Debiasing via Contrastive Reflection for Fairness Enhancement in Large Language Models
Distilling the Essence, Discarding the Dross: Improving Fairness in Multimodal Large Language Models via Historical Reflection-Guided Prompt Optimization
Enhancing Fairness in Decision-Making of Natural Language Understanding Systems: An Intersectional Bias Debiasing Model via Information Theory-Based Disentanglement
BATED: Learning Fair Representation for Pre-Trained Language Models via Biased Teacher-Guided Disentanglement
Data-Centric Explainable Debiasing for Improving Fairness in Pre-Trained Language Models
Mitigating Social Biases of Pre-Trained Language Models via Contrastive Self-Debiasing with Double Data Augmentation
A Survey on Fairness in Large Language Models
Measuring and Mitigating Language Model Biases in Abusive Language Detection
Improving Abusive Language Detection with Online Interaction Network
In-Context Learning上下文学习
5Bottom-Up Competition Based on Label Hierarchy Trees for In-Context Learning with Large Label Space
From Fake to Real: Mitigating Out-of-Distribution Bias in In-Context Learning via Feedback Supervision from Large Language Models
Toward Robust In-Context Learning: Leveraging Out-of-Distribution Proxies for Target Inaccessible Demonstration Retrieval
Retrieval Augmentation for Out-of-Distribution Robustness in Non-Knowledge Intensive In-Context Learning
Shortcut Learning in In-Context Learning: A Survey
Other NLP Applications其他自然语言处理应用
10TACIT: A Target-Agnostic Feature Disentanglement Framework for Cross-Domain Text Classification
Causal Keyword Driven Reliable Text Classification with Large Language Model Feedback
Counterfactual Contrastive Learning for Robust Text Classification Based on Word Group Search
DGJA: Dependency Graph-Enhanced Joint Attention Structure for Multimodal Sarcasm Detection
Self-Supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness
Topological Enhanced Graph Neural Networks for Semi-Supervised Node Classification
Guiding Ontology Translation with Hubness-Aware Translation Memory
Weak-PMLC: A Large-Scale Framework for Multi-Label Policy Classification Based on Extremely Weak Supervision
SUNET: Speaker-Utterance Interaction Graph Neural Network for Emotion Recognition in Conversations
Label Prompt for Multi-Label Text Classification
AI for Library and Information Science图书情报智能
1Funded Research 科研项目
Projects 项目
China Postdoctoral Science Foundation 中国博士后科学基金第76批面上资助
Research on mitigating out-of-distribution bias in large language model in-context learning.
大语言模型上下文学习中的分布外偏见缓解方法研究。
Jilin Provincial Natural Science Foundation 吉林省自然科学基金面上项目
Research on shortcut learning mitigation for large language model in-context learning.
面向大语言模型上下文学习的捷径学习缓解方法研究。
Jilin Provincial Department of Education 吉林省教育厅科学研究项目
Excellent Young Scholar research project.
优秀青年项目。