研究方向
基于大语言模型的语义理解与文本生成；跨模态语义理解；
AI+教育（http://www.chinese-pku.com）
科研/教育经历
2005 ~ —— 讲师/副教授，北京大学信息科学技术学院
2003 ~ 2005， 博士后研究，北京大学
2000 ~ 2003， 博士研究生，北京大学
科研项目
[1] 国家自然科学基金面上项目: 面向阅读理解的问题自动生成关键技术研究. 2021.01-2024.12. 主持.
[2] 国家自然科学基金面上项目: 基于文档的智能问答的关键技术研究与资源建设. 2018.01-2021.12. 主持.
[3] 国家自然科学基金面上项目: 基于汉语话题的句际关系自动分析研究. 2014.01-2017.12. 主持.
[4] 国家自然科学基金青年项目: 基于词语独异性特征的大规模词义标注语料库自动构建研究. 2008.01--2010.12. 主持.
[5] 国家社科基金后期资助项目: 面向语言信息处理的现代汉语并列结构研究. 2012.01-2013.06. 主持.
[6] 国家社会科学基金青年项目: 面向网络文本的词语情感义自动标注研究. 2008.06--2010.12. 主持.
[7] 国家社科基金重大项目: 面向网络文本的多视角语义分析方法、语言知识库及平台建设研究. 2013.01-2017.12，子课题负责人。
[8] 国家863项目: 面向基础教育的类人智能知识理解与推理关键技术. 2015.01-2017.12，课题骨干。
[9] 国家863项目：面向汉语语音合成的言语语义计算模型研究. 2007.07--2009.12，副组长。
[10] 人民教育出版社合作项目: 中国儿童分级阅读文本标准研制，2020.09--2021.12，主持
[11] 主持其他产学研合作项目7项，资源成果转让若干.
科研获奖
[1] 2011年，“综合型语言知识库”，国家科学技术进步二等奖.
[2] 2020年，“多情景跨领域中文文本智能校对关键技术及应用”，北京市科学技术进步二等奖.
Selected Publications（* Corresponding Author）
[1] Sanwoo Lee, Kun Liang, Yunfang Wu*. Composable Cross-prompt Essay Scoring by Merging Models. EMNLP-2025.
[2] Wang Cai, Hsiuyuan Huang, Zhixiang Wang, Yunfang Wu*. Beyond Demonstrations: Dynamic Vector Construction from Latent Representations. EMNLP-2025.
[3] Zichen Wu, Hsiuyuan Huang, Yunfang Wu*. Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing. Findings of EMNLP-2025.
[4] Chenming Tang, Zhixiang Wang, Hao Sun,Yunfang Wu*. Large Language Models Might Not Care What You Are Saying: Prompt Format Beats Descriptions. Findings of EMNLP-2025.
[5] Zhaoxi Zhang, Sanwoo Lee, Zhixiang Wang, Yunfang Wu*. 3DM: Distill, Dynamic Drop, and Merge for Debiasing Multi-modal Large Language Models. Findings of ACL-2025.
[6] Sanwoo Lee, Jiahao Liu, Qifan Wang, Jingang Wang, Xunliang Cai, Yunfang Wu*. Dynamic Fisher-weighted Model Merging via Bayesian Optimization. NAACL-2025.
[7] Chenming Tang, Zhixiang Wang, Yunfang Wu*. SCOI: Syntax-augmented Coverage-based In-context Example Selection for Machine Translation. EMNLP-2024.
[8] Sanwoo Lee, Yida Cai, Desong Meng, Ziyang Wang, Yunfang Wu*. Unleashing Large Language Models' Proficiency in Zero-shot Essay Scoring. Findings of EMNLP-2024.
[9] Fanyi Qu, Hao Sun, Yunfang Wu*. Unsupervised Distractor Generation via Large Language Model Distilling and Counterfactual Contrastive Decoding. Findings of ACL-2024.
[10] Chenming Tang, Fanyi Qu, Yunfang Wu*. Ungrammatical-syntax-based In-context Example Selection for Grammatical Error Correction. NAACL-2024.
[11] Ziyang Wang, Shanyu Li, HsiuYuan Huang, Yunfang Wu*. FPT: Feature Prompt Tuning for Few-shot Readability Assessment. NAACL-2024.
[12] Ming Zhang, Ke Chang, Yunfang Wu*. Multi-modal Semantic Understanding with Contrastive Cross-modal Feature Alignment. COLING-2024.
[13] Zichen Wu, HsiuYuan Huang, Fanyi Qu and Yunfang Wu*. Mixture-of-Prompt-Experts for Multi-modal Semantic Understanding. COLING-2024.
[14] Chenming Tang, Xiuyu Wu, Yunfang Wu*. Are Pre-trained Language Models Useful for Model Ensemble in Chinese Grammatical Error Correction? ACL-2023.
[15] Wenbiao Li, Wang Ziyang and Yunfang Wu*. A Unified Neural Network Model for Readability Assessment with Feature Projection and Length-Balanced Loss. EMNLP-2022.
[16] Xiuyu Wu and Yunfang Wu*. From Spelling to Grammar: A New Framework for Chinese Grammatical Error Correction. Findings of EMNLP-2022.
[17] Rui Sun, Xiuyu Wu and Yunfang Wu*. An Error-Guided Correction Model for Chinese Spelling Error Correction. Findings of EMNLP-2022.
[18] Zichen Wu, Xin Jia, Fanyi Qu and Yunfang Wu*. Enhancing Pre-trained Models with Text Structure Knowledge for Question Generation. COLING-2022.
[19] Ming Zhang, Shuai Dou, Ziyang Wang, Yunfang Wu*. Focus-Driven Contrastive Learniang for Medical Question Summarization. COLING-2022.
[20] Xiuyu Wu, Jingsong Yu, Xu Sun and Yunfang Wu*. Position Offset Label Prediction for Grammatical Error Correction. COLING-2022.
[21] Fanyi Qu, Xin Jia, Yunfang Wu*. Asking Questions Like Educational Experts: Automatically Generating Question-Answer Pairs on Real-World Examination Data. EMNLP-2021.
[22] Xin Jia, Wenjie Zhou, Xu Sun, Yunfang Wu*. EQG-RACE: Examination-Type Question Generation. AAAI-2021.
[23] Xin Jia, Wenjie Zhou, Xu Sun, Yunfang Wu*. How to Ask Good Questions? Try to Leverage Paraphrases. ACL-2020.
[24] Xiaorui Zhou, Senlin Luo, Yunfang Wu*. 2020. Co-Attention Hierarchical Network: Generating Coherent Long Distractors for Reading Comprehension. AAAI-2020.
