Eric Wallace

发表

Compositional Questions Do Not Necessitate Multi-hop Reasoning pdf

Sameer Singh, Hannaneh Hajishirzi, Luke Zettlemoyer, 2019, ACL.

Trick Me If You Can: Adversarial Writing of Trivia Challenge Questions pdf

Jordan Boyd-Graber, Jordan L. Boyd-Graber, Eric Wallace, 2018, ACL.

2018 Human Systems Conference. Human Systems in Emerging Domains: Autonomy, Human Augmentation and Cyber. Held in Springfield, Virginia on 13-14 March 2018

Peggy Wu, Glenn Gunzelmann, Denise Nicholson, 2018 .

Universal Adversarial Triggers for Attacking and Analyzing NLP

Sameer Singh, Matt Gardner, Eric Wallace, 2019, EMNLP.

Universal Adversarial Triggers for NLP pdf

Sameer Singh, Matt Gardner, Eric Wallace, 2019, ArXiv.

Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation pdf

Shi Feng, Sahil Singla, Soheil Feizi, 2019, ICML.

A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features': Learning from Incorrectly Labeled Data

Eric Wallace, Eric Wallace, 2019, Distill.

Do NLP Models Know Numbers? Probing Numeracy in Embeddings pdf

Sameer Singh, Sujian Li, Matt Gardner, 2019, EMNLP.

AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models pdf

Sameer Singh, Junlin Wang, Matt Gardner, 2019, EMNLP.

Trick Me If You Can: Human-in-the-loop Generation of Adversarial Question Answering Examples

Shi Feng, Ikuya Yamada, Jordan L. Boyd-Graber, 2019, Trans. Assoc. Comput. Linguistics.

Detoxifying Language Models Risks Marginalizing Minority Voices pdf

Dan Klein, Maarten Sap, Suchin Gururangan, 2021, NAACL.

Concealed Data Poisoning Attacks on NLP Models

Shi Feng, Eric Wallace, Tony Z. Zhao, 2021, NAACL.

Analyzing Dynamic Adversarial Training Data in the Limit pdf

Robin Jia, Eric Wallace, Douwe Kiela, 2021, ArXiv.

Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models pdf

Fabio Petroni, Sebastian Riedel, IV RobertL.Logan, 2021, FINDINGS.