b'Eric Wallace'

research

∙ 05/19/2022

Automated Crossword Solving

We present the Berkeley Crossword Solver, a state-of-the-art approach fo...

Eric Wallace, et al. ∙

research

∙ 04/12/2022

InCoder: A Generative Model for Code Infilling and Synthesis

Code is seldom written in a single left-to-right pass and is instead rep...

Daniel Fried, et al. ∙

research

∙ 02/14/2022

Deduplicating Training Data Mitigates Privacy Risks in Language Models

Past work has shown that large language models are susceptible to privac...

Nikhil Kandpal, et al. ∙

research

∙ 10/16/2021

Analyzing Dynamic Adversarial Training Data in the Limit

To create models that are robust across a wide range of test inputs, tra...

Eric Wallace, et al. ∙

research

∙ 06/24/2021

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

Prompting language models (LMs) with training examples and task descript...

Robert L. Logan IV, et al. ∙

research

∙ 04/13/2021

Detoxifying Language Models Risks Marginalizing Minority Voices

Language models (LMs) must be both safe and equitable to be responsibly ...

Albert Xu, et al. ∙

research

∙ 02/19/2021

Calibrate Before Use: Improving Few-Shot Performance of Language Models

GPT-3 can perform numerous tasks when provided a natural language prompt...

Tony Z. Zhao, et al. ∙

research

∙ 12/14/2020

Extracting Training Data from Large Language Models

It has become common to publish large (billion parameter) language model...

Nicholas Carlini, et al. ∙

research

∙ 10/29/2020

AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts

The remarkable success of pretrained language models has motivated the s...

Taylor Shin, et al. ∙

research

∙ 10/23/2020

Customizing Triggers with Concealed Data Poisoning

Adversarial attacks alter NLP model predictions by perturbing test-time ...

Eric Wallace, et al. ∙

research

∙ 10/12/2020

Gradient-based Analysis of NLP Models is Manipulable

Gradient-based analysis methods, such as saliency map visualizations and...

Junlin Wang, et al. ∙

research

∙ 08/10/2020

Trustworthy AI Inference Systems: An Industry Research View

In this work, we provide an industry research view for approaching the d...

Rosario Cammarota, et al. ∙

research

∙ 04/30/2020

Imitation Attacks and Defenses for Black-box Machine Translation Systems

We consider an adversary looking to steal or attack a black-box machine ...

Eric Wallace, et al. ∙

research

∙ 04/13/2020

Pretrained Transformers Improve Out-of-Distribution Robustness

Although pretrained Transformers such as BERT achieve high accuracy on i...

Dan Hendrycks, et al. ∙

research

∙ 04/06/2020

Evaluating NLP Models via Contrast Sets

Standard test sets for supervised learning evaluate in-distribution gene...

Matt Gardner, et al. ∙

research

∙ 02/26/2020

Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers

Since hardware resources are limited, the objective of training deep lea...

Zhuohan Li, et al. ∙

research

∙ 09/19/2019

AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models

Neural NLP models are increasingly accurate but are imperfect and opaque...

Eric Wallace, et al. ∙

research

∙ 09/17/2019

Do NLP Models Know Numbers? Probing Numeracy in Embeddings

The ability to understand and work with numbers (numeracy) is critical f...

Eric Wallace, et al. ∙

research

∙ 08/20/2019

Universal Adversarial Triggers for Attacking and Analyzing NLP

Adversarial examples highlight model vulnerabilities and are useful for ...

Eric Wallace, et al. ∙

research

∙ 08/20/2019

Universal Adversarial Triggers for NLP

Adversarial examples highlight model vulnerabilities and are useful for ...

Eric Wallace, et al. ∙

research

∙ 06/07/2019

Compositional Questions Do Not Necessitate Multi-hop Reasoning

Multi-hop reading comprehension (RC) questions are challenging because t...

Sewon Min, et al. ∙

research

∙ 05/14/2019

Misleading Failures of Partial-input Baselines

Recent work establishes dataset difficulty and removes annotation artifa...

Shi Feng, et al. ∙

research

∙ 02/01/2019

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

Current methods to interpret deep learning models by generating saliency...

Sahil Singla, et al. ∙

research

∙ 09/08/2018

Interpreting Neural Networks With Nearest Neighbors

Local model interpretation methods explain individual predictions by ass...

Eric Wallace, et al. ∙

research

∙ 09/07/2018

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

Modern natural language processing systems have been touted as approachi...

Eric Wallace, et al. ∙

research

∙ 04/20/2018

Right Answer for the Wrong Reason: Discovery and Mitigation

Exposing the weaknesses of neural models is crucial for improving their ...

Shi Feng, et al. ∙

Eric Wallace

Featured Co-authors

Luke Zettlemoyer

Noah A. Smith

Dawn Song

Sebastian Riedel

Kurt Keutzer

Joseph E. Gonzalez

Hannaneh Hajishirzi

Jonathan Berant

Kamalika Chaudhuri

Douwe Kiela

Sameer Singh

Automated Crossword Solving

InCoder: A Generative Model for Code Infilling and Synthesis

Deduplicating Training Data Mitigates Privacy Risks in Language Models

Analyzing Dynamic Adversarial Training Data in the Limit

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

Detoxifying Language Models Risks Marginalizing Minority Voices

Calibrate Before Use: Improving Few-Shot Performance of Language Models

Extracting Training Data from Large Language Models

AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts

Customizing Triggers with Concealed Data Poisoning

Gradient-based Analysis of NLP Models is Manipulable

Trustworthy AI Inference Systems: An Industry Research View

Imitation Attacks and Defenses for Black-box Machine Translation Systems

Pretrained Transformers Improve Out-of-Distribution Robustness

Evaluating NLP Models via Contrast Sets

Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers

AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models

Do NLP Models Know Numbers? Probing Numeracy in Embeddings

Universal Adversarial Triggers for Attacking and Analyzing NLP

Universal Adversarial Triggers for NLP

Compositional Questions Do Not Necessitate Multi-hop Reasoning

Misleading Failures of Partial-input Baselines

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

Interpreting Neural Networks With Nearest Neighbors

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

Right Answer for the Wrong Reason: Discovery and Mitigation