106 citations · 307 across the 18 of their papers we have counts for
18 papers
Mitigating Extrinsic Gender Bias for Bangla Classification Tasks
Sajib Kumar Saha Joy, Arman Hassan Mahy, Meherin Sultana +4
In this study, we investigate extrinsic gender bias in Bangla pretrained language models, a largely underexplored area in low-resource languages. To assess this bias, we construct…
A Minimalist Prompt for Zero-Shot Policy Learning
Meng Song, Xuezhi Wang, Tanay Biradar +2
Transformer-based methods have exhibited significant generalization ability when prompted with target-domain demonstrations or example solutions during inference. Although demonstr…
Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals
Ananth Balashankar, Xuezhi Wang, Yao Qin +5
Counterfactual Data Augmentation (CDA) is a commonly used technique for improving robustness in natural language classifiers. However, one fundamental challenge is how to discover…
Towards Robust Prompts on Vision-Language Models
Jindong Gu, Ahmad Beirami, Xuezhi Wang +3
With the advent of vision-language models (VLMs) that can perform in-context and prompt-based learning, how can we design prompting approaches that robustly generalize to distribut…
A Mixed-Methods Approach to Understanding User Trust after Voice Assistant Failures
Amanda Baughan, Allison Mercurio, Ariel Liu +3
Despite huge gains in performance in natural language understanding via large language models in recent years, voice assistants still often fail to meet user expectations. In this…
What Are Effective Labels for Augmented Data? Improving Calibration and Robustness with AutoLabel
Yao Qin, Xuezhi Wang, Balaji Lakshminarayanan +2
A wide breadth of research has devised data augmentation approaches that can improve both accuracy and generalization performance for neural networks. However, augmented data can e…
Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiers
Jieyu Zhao, Xuezhi Wang, Yao Qin +2
Large pre-trained language models have shown remarkable performance over the past few years. These models, however, sometimes learn superficial features from the dataset and cannot…
Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation
Yao Qin, Chiyuan Zhang, Ting Chen +3
We investigate the robustness of vision transformers (ViTs) through the lens of their special patch-based architectural structure, i.e., they process an image as a sequence of imag…
Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning
Yuyan Wang, Xuezhi Wang, Alex Beutel +3
As multi-task models gain popularity in a wider range of machine learning applications, it is becoming increasingly important for practitioners to understand the fairness implicati…
Measuring Model Fairness under Noisy Covariates: A Theoretical Perspective
Flavien Prost, Pranjal Awasthi, Nick Blumm +7
In this work we study the problem of measuring the fairness of a machine learning model under noisy information. Focusing on group fairness metrics, we investigate the particular b…
Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Information
Pranjal Awasthi, Alex Beutel, Matthaeus Kleindessner +2
Training and evaluation of fair classifiers is a challenging problem. This is partly due to the fact that most fairness metrics of interest depend on both the sensitive attribute i…
Measuring Recommender System Effects with Simulated Users
Sirui Yao, Yoni Halpern, Nithum Thain +6
Imagine a food recommender system -- how would we check if it is \emph{causing} and fostering unhealthy eating habits or merely reflecting users' interests? How much of a user's ex…
CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generation
Tianlu Wang, Xuezhi Wang, Yao Qin +5
NLP models are shown to suffer from robustness issues, i.e., a model's prediction can be easily changed under small perturbations to the input. In this work, we present a Controlle…
Measuring and Reducing Gendered Correlations in Pre-trained Models
Kellie Webster, Xuezhi Wang, Ian Tenney +6
Pre-trained models have revolutionized natural language understanding. However, researchers have found they can encode artifacts undesired in many applications, such as professions…
Improving Calibration through the Relationship with Adversarial Robustness
Yao Qin, Xuezhi Wang, Alex Beutel +1
Neural networks lack adversarial robustness, i.e., they are vulnerable to adversarial examples that through small perturbations to inputs cause incorrect predictions. Further, trus…
Fairness without Demographics through Adversarially Reweighted Learning
Preethi Lahoti, Alex Beutel, Jilin Chen +5
Much of the previous machine learning (ML) fairness literature assumes that protected features such as race and sex are present in the dataset, and relies upon them to mitigate fai…
Practical Compositional Fairness: Understanding Fairness in Multi-Component Recommender Systems
Xuezhi Wang, Nithum Thain, Anu Sinha +4
How can we build recommender systems to take into account fairness? Real-world recommender systems are often composed of multiple models, built by multiple teams. However, most res…
Transfer of Machine Learning Fairness across Domains
Candice Schumann, Xuezhi Wang, Alex Beutel +3
If our models are used in new or unexpected cases, do we know if they will make fair predictions? Previously, researchers developed ways to debias a model for a single problem doma…