92 citations · 93 across the 5 of their papers we have counts for
5 papers
Controlling Bias Exposure for Fair Interpretable Predictions
Zexue He, Yu Wang, Julian McAuley +1
Recent work on reducing bias in NLP models usually focuses on protecting or isolating information related to a sensitive attribute (like gender or race). However, when sensitive in…
Leashing the Inner Demons: Self-Detoxification for Language Models
Canwen Xu, Zexue He, Zhankui He +1
Language models (LMs) can reproduce (or amplify) toxic language seen during training, which poses a risk to their practical application. In this paper, we conduct extensive experim…
Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation
An Yan, Zexue He, Xing Lu +5
Radiology report generation aims at generating descriptive text from radiology images automatically, which may present an opportunity to improve radiology reporting and interpretat…
Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding
Zexue He, Bodhisattwa Prasad Majumder, Julian McAuley
Written language carries explicit and implicit biases that can distract from meaningful signals. For example, letters of reference may describe male and female candidates different…
Learning Robust Representations by Projecting Superficial Statistics Out
Haohan Wang, Zexue He, Zachary C. Lipton +1
Despite impressive performance as evaluated on i.i.d. holdout data, deep neural networks depend heavily on superficial statistics of the training data and are liable to break under…