Zexue He

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 37

Top Topics

Conditional Mutual Information

Weakly Supervised

Visual Recognition

Top Venues

EMNLP (Findings)

Publications

Jessica Maria Echterhoff, Yao Liu, Abeer Alessa, Julian J. McAuley, Zexue He
Cognitive Bias in High-Stakes Decision-Making with LLMs. CoRR (2024)
Jiarui Jin, Zexue He, Mengyue Yang, Weinan Zhang, Yong Yu, Jun Wang, Julian J. McAuley
InfoRank: Unbiased Learning-to-Rank via Conditional Mutual Information Minimization. WWW (2024)
Jiarui Jin, Zexue He, Mengyue Yang, Weinan Zhang, Yong Yu, Jun Wang, Julian J. McAuley
InfoRank: Unbiased Learning-to-Rank via Conditional Mutual Information Minimization. CoRR (2024)
Zexue He, Leonid Karlinsky, Donghyun Kim, Julian J. McAuley, Dmitry Krotov, Rogério Feris
CAMELoT: Towards Large Language Models with Training-Free Consolidated Associative Memory. CoRR (2024)
Yu Wang, Zeyuan Zhang, Julian J. McAuley, Zexue He
LVCHAT: Facilitating Long Video Comprehension. CoRR (2024)
Yu Wang, Zexue He, Zhankui He, Hao Xu, Julian J. McAuley
Deciphering Compatibility Relationships with Textual Descriptions via Extraction and Explanation. AAAI (2024)
Yu Wang, Ruihan Wu, Zexue He, Xiusi Chen, Julian J. McAuley
Large Scale Knowledge Washing. CoRR (2024)
Zexue He, Marco Túlio Ribeiro, Fereshte Khani
Targeted Data Generation: Finding and Fixing Model Weaknesses. CoRR (2023)
Zexue He, Yu Wang, An Yan, Yao Liu, Eric Y. Chang, Amilcare Gentili, Julian J. McAuley, Chun-Nan Hsu
MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation. CoRR (2023)
Zexue He, An Yan, Amilcare Gentili, Julian J. McAuley, Chun-Nan Hsu
"Nothing Abnormal": Disambiguating Medical Reports via Contrastive Knowledge Infusion. AAAI (2023)
Bodhisattwa Prasad Majumder, Zexue He, Julian J. McAuley
InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions. EMNLP (2023)
Noveen Sachdeva, Zexue He, Wang-Cheng Kang, Jianmo Ni, Derek Zhiyuan Cheng, Julian J. McAuley
Farzi Data: Autoregressive Data Distillation. CoRR (2023)
Zexue He, Graeme Blackwood, Rameswar Panda, Julian J. McAuley, Rogério Feris
Synthetic Pre-Training Tasks for Neural Machine Translation. ACL (Findings) (2023)
An Yan, Yu Wang, Yiwu Zhong, Zexue He, Petros Karypis, Zihan Wang, Chengyu Dong, Amilcare Gentili, Chun-Nan Hsu, Jingbo Shang, Julian J. McAuley
Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models. CoRR (2023)
An Yan, Yu Wang, Yiwu Zhong, Chengyu Dong, Zexue He, Yujie Lu, William Yang Wang, Jingbo Shang, Julian J. McAuley
Learning Concise and Descriptive Attributes for Visual Recognition. ICCV (2023)
Zexue He, An Yan, Amilcare Gentili, Julian J. McAuley, Chun-Nan Hsu
"Nothing Abnormal": Disambiguating Medical Reports via Contrastive Knowledge Infusion. CoRR (2023)
An Yan, Yu Wang, Yiwu Zhong, Chengyu Dong, Zexue He, Yujie Lu, William Wang, Jingbo Shang, Julian J. McAuley
Learning Concise and Descriptive Attributes for Visual Recognition. CoRR (2023)
Zexue He, Marco Túlio Ribeiro, Fereshte Khani
Targeted Data Generation: Finding and Fixing Model Weaknesses. ACL (1) (2023)
Yu Wang, Zexue He, Zhankui He, Hao Xu, Julian J. McAuley
Deciphering Compatibility Relationships with Textual Descriptions via Extraction and Explanation. CoRR (2023)
Zexue He, Yu Wang, An Yan, Yao Liu, Eric Y. Chang, Amilcare Gentili, Julian J. McAuley, Chun-Nan Hsu
MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation. EMNLP (2023)
Canwen Xu, Zexue He, Zhankui He, Julian J. McAuley
Leashing the Inner Demons: Self-Detoxification for Language Models. CoRR (2022)
Zexue He, Yu Wang, Julian J. McAuley, Bodhisattwa Prasad Majumder
Controlling Bias Exposure for Fair Interpretable Predictions. CoRR (2022)
Zexue He, Yu Wang, Julian J. McAuley, Bodhisattwa Prasad Majumder
Controlling Bias Exposure for Fair Interpretable Predictions. EMNLP (Findings) (2022)
Bodhisattwa Prasad Majumder, Zexue He, Julian J. McAuley
InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions. CoRR (2022)
Canwen Xu, Zexue He, Zhankui He, Julian J. McAuley
Leashing the Inner Demons: Self-Detoxification for Language Models. AAAI (2022)
Zexue He, Graeme Blackwood, Rameswar Panda, Julian J. McAuley, Rogério Feris
Synthetic Pre-Training Tasks for Neural Machine Translation. CoRR (2022)
An Yan, Zexue He, Xing Lu, Jiang Du, Eric Y. Chang, Amilcare Gentili, Julian McAuley, Chun-Nan Hsu
Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation. CoRR (2021)
An Yan, Zexue He, Xing Lu, Jiang Du, Eric Y. Chang, Amilcare Gentili, Julian McAuley, Chun-Nan Hsu
Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation. EMNLP (Findings) (2021)
Zexue He, Bodhisattwa Prasad Majumder, Julian McAuley
Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding. EMNLP (Findings) (2021)
Zexue He, Bodhisattwa Prasad Majumder, Julian McAuley
Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding. CoRR (2021)
Zexue He, Li Zhu, Minjie Li, Jinyao Li, Yiran Chen, Yanlin Luo
Rapid and high-quality 3D fusion of heterogeneous CT and MRI data for the human brain. Sci. China Inf. Sci. 62 (10) (2019)
Haohan Wang, Zexue He, Zachary C. Lipton, Eric P. Xing
Learning Robust Representations by Projecting Superficial Statistics Out. CoRR (2019)
Haohan Wang, Zexue He, Zachary C. Lipton, Eric P. Xing
Learning Robust Representations by Projecting Superficial Statistics Out. ICLR (2019)
Fuli Luo, Tianyu Liu, Zexue He, Qiaolin Xia, Zhifang Sui, Baobao Chang
Leveraging Gloss Knowledge in Neural Word Sense Disambiguation by Hierarchical Co-Attention. EMNLP (2018)
Xiaochuan Wang, Ning Su, Zexue He, Yiqun Liu, Shaoping Ma
A Large-Scale Study of Mobile Search Examination Behavior. SIGIR (2018)
Xiangsheng Li, Yiqun Liu, Jiaxin Mao, Zexue He, Min Zhang, Shaoping Ma
Understanding Reading Attention Distribution during Relevance Judgement. CIKM (2018)
Jiaxin Mao, Yiqun Liu, Noriko Kando, Zexue He, Min Zhang, Shaoping Ma
A Two-Stage Model for User's Examination Behavior in Mobile Search. CHIIR (2018)