Bairu Hou is a 3rd-year Ph.D. student of Department of Computer Science, UC Santa Barbara. He is now working with Prof. Shiyu Chang. His research interest mainly lies in natural language processing and speech recognition.
Currently, he focuses on large langauge models, adversarial robustness in natural language processing, and diffusion models. He also has some experiences on natural logic and semantics.
He was a research assistant in THUNLP Group supervised by Prof. Zhiyuan Liu from 2018 to 2021.
Most recent publications on Google Scholar.
‡ indicates equal contribution.
Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
Jiabao Ji‡, Bairu Hou‡, Alexander Robey‡, George J Pappas, Hamed Hassani, Yang Zhang, Eric Wong, Shiyu Chang
Arxiv
Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling
Bairu Hou, Yujian Liu, Kaizhi Qian, Jacob Andreas, Shiyu Chang, Yang Zhang
ICML'24: International Conference on Machine Learning
Advancing the Robustness of Large Language Models through Self-Denoised Smoothing
Jiabao Ji‡, Bairu Hou‡, Zhen Zhang‡, Guanhua Zhang‡, Wenqi Fan, Qing Li, Yang Zhang, Gaowen Liu, Sijia Liu, Shiyu Chang
NAACL'24
Improving Diffusion Models for Scene Text Editing with Dual Encoders
Jiabao Ji, Guanhua Zhang, Zhaowen Wang, Bairu Hou, Zhifei Zhang, Brian Price, Shiyu Chang
TMLR: Transactions on Machine Learning Research
PromptBoosting: Black-Box Text Classification with Ten Forward Passes
Bairu Hou, Joe O'Connor, Jacob Andreas, Shiyu Chang, Yang Zhang
ICML'23: International Conference on Machine Learning
TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization
Bairu Hou, Jinghan Jia, Yihua Zhang, Guanhua Zhang, Yang Zhang, Sijia Liu, Shiyu Chang
ICLR'23: International Conference on Learning Representations
OpenAttack: An Open-source Textual Adversarial Attack Toolkit
Guoyang Zeng, Fanchao Qi, Qianrui Zhou, Tingji Zhang, Bairu Hou, Yuan Zang, Zhiyuan Liu, Maosong Sun
ACL'21: Annual Meeting of the Association for Computational Linguistics
Try to Substitute: An Unsupervised Chinese Word Sense Disambiguation Method Based on HowNet
Bairu Hou, Fanchao Qi, Yuan Zang, Xurui Zhang, Zhiyuan Liu, Maosong Sun
COLING'20: International Conference on Computational Linguistics
Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations
Yuan Zang‡, Bairu Hou‡, Fanchao Qi‡, Zhiyuan Liu, Xiaojun Meng, Maosong Sun
Arxiv
Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
Jiabao Ji‡, Bairu Hou‡, Alexander Robey‡, George J Pappas, Hamed Hassani, Yang Zhang, Eric Wong, Shiyu Chang
Arxiv
Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling
Bairu Hou, Yujian Liu, Kaizhi Qian, Jacob Andreas, Shiyu Chang, Yang Zhang
ICML'24: International Conference on Machine Learning
Advancing the Robustness of Large Language Models through Self-Denoised Smoothing
Jiabao Ji‡, Bairu Hou‡, Zhen Zhang‡, Guanhua Zhang‡, Wenqi Fan, Qing Li, Yang Zhang, Gaowen Liu, Sijia Liu, Shiyu Chang
NAACL'24
Improving Diffusion Models for Scene Text Editing with Dual Encoders
Jiabao Ji, Guanhua Zhang, Zhaowen Wang, Bairu Hou, Zhifei Zhang, Brian Price, Shiyu Chang
TMLR: Transactions on Machine Learning Research
PromptBoosting: Black-Box Text Classification with Ten Forward Passes
Bairu Hou, Joe O'Connor, Jacob Andreas, Shiyu Chang, Yang Zhang
ICML'23: International Conference on Machine Learning
TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization
Bairu Hou, Jinghan Jia, Yihua Zhang, Guanhua Zhang, Yang Zhang, Sijia Liu, Shiyu Chang
ICLR'23: International Conference on Learning Representations
OpenAttack: An Open-source Textual Adversarial Attack Toolkit
Guoyang Zeng, Fanchao Qi, Qianrui Zhou, Tingji Zhang, Bairu Hou, Yuan Zang, Zhiyuan Liu, Maosong Sun
ACL'21: Annual Meeting of the Association for Computational Linguistics
Try to Substitute: An Unsupervised Chinese Word Sense Disambiguation Method Based on HowNet
Bairu Hou, Fanchao Qi, Yuan Zang, Xurui Zhang, Zhiyuan Liu, Maosong Sun
COLING'20: International Conference on Computational Linguistics
Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations
Yuan Zang‡, Bairu Hou‡, Fanchao Qi‡, Zhiyuan Liu, Xiaojun Meng, Maosong Sun
Arxiv