Viégas, Fernanda

SmoothGrad: removing noise by adding noise

Smilkov, D., Thorat, N., Kim, B., Viégas, F., & Wattenberg, M. (2017) · arXiv

Explainable Artificial Intelligence (XAI)Software Testing and Debugging Techniques

Cited by 1,467

How to use t-SNE effectively

Wattenberg, M., Viégas, F., & Johnson, I. (2016) · Distill

Technical Engine Diagnostics and MonitoringFault Detection and Control Systems

Cited by 854

The Hidden Order of Wikipedia

Viégas, F. B., Wattenberg, M., & McKeon, M. M. (2007) · Lecture Notes in Computer Science

Wikis in Education and CollaborationOpen Source Software Innovations

Cited by 195

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Li, K., Patel, O., Viégas, F., Pfister, H., & Wattenberg, M. (2023) · arXiv

Deception detection and forensic psychologyTopic Modeling

Cited by 184

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Li, K., Patel, O., Viégas, F., Pfister, H., & Wattenberg, M. (2023) · Advances in Neural Information Processing Systems 36

Deception detection and forensic psychologyTopic Modeling

Cited by 117

An Interpretability Illusion for BERT

Bolukbasi, T., Pearce, A., Yuan, A., Coenen, A., Reif, E., Viégas, F., & Wattenberg, M. (2021) · arXiv

Explainable Artificial Intelligence (XAI)Topic Modeling

Cited by 113

Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task

Li, K., Hopkins, A. K., Bau, D., Viégas, F., Pfister, H., & Wattenberg, M. (2022) · arXiv

Explainable Artificial Intelligence (XAI)Artificial Intelligence in Games

Cited by 61

Measuring and Controlling Instruction (In)Stability in Language Model Dialogs

Li, K., Liu, T., Bashkansky, N., Bau, D., Viégas, F., Pfister, H., & Wattenberg, M. (2024) · arXiv

Speech and dialogue systemsTopic Modeling

Cited by 23