b'Eric Wallace'

research

∙ 09/11/2023

Privacy Side Channels in Machine Learning Systems

Most current approaches for protecting privacy in machine learning (ML) ...

0 Edoardo Debenedetti, et al. ∙

research

∙ 08/08/2023

SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore

The legality of training language models (LMs) on copyrighted or otherwi...

0 Sewon Min, et al. ∙

research

∙ 05/25/2023

The False Promise of Imitating Proprietary LLMs

An emerging method to cheaply improve a weaker language model is to fine...

0 Arnav Gudibande, et al. ∙

research

∙ 05/01/2023

Poisoning Language Models During Instruction Tuning

Instruction-tuned LMs such as ChatGPT, FLAN, and InstructGPT are finetun...

0 Alexander Wan, et al. ∙

research

∙ 01/30/2023

Extracting Training Data from Diffusion Models

Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion ha...

0 Nicholas Carlini, et al. ∙

research

∙ 11/15/2022

Large Language Models Struggle to Learn Long-Tail Knowledge

The internet contains a wealth of knowledge – from the birthdays of hist...

0 Nikhil Kandpal, et al. ∙

research

∙ 05/19/2022

Automated Crossword Solving

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

17 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...

6 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...

0 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...

0 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...

0 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 ...

12 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...

6 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...

0 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...

0 Taylor Shin, et al. ∙

research

∙ 10/23/2020

Customizing Triggers with Concealed Data Poisoning

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

0 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...

11 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...

37 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 ...

0 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...

0 Dan Hendrycks, et al. ∙

research

∙ 04/06/2020

Evaluating NLP Models via Contrast Sets

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

0 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...

0 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...

0 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...

0 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 ...

0 Eric Wallace, et al. ∙

research

∙ 08/20/2019

Universal Adversarial Triggers for NLP

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

0 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...

6 Sewon Min, et al. ∙

research

∙ 05/14/2019

Misleading Failures of Partial-input Baselines

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

0 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...

2 Sahil Singla, et al. ∙

research

∙ 09/08/2018

Interpreting Neural Networks With Nearest Neighbors

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

0 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...

0 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 ...

0 Shi Feng, et al. ∙

Eric Wallace

Featured Co-authors