research
∙
09/11/2023
Privacy Side Channels in Machine Learning Systems
Most current approaches for protecting privacy in machine learning (ML) ...
share
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...
research
∙
05/25/2023
The False Promise of Imitating Proprietary LLMs
An emerging method to cheaply improve a weaker language model is to fine...
research
∙
05/01/2023
Poisoning Language Models During Instruction Tuning
Instruction-tuned LMs such as ChatGPT, FLAN, and InstructGPT are finetun...
research
∙
01/30/2023
Extracting Training Data from Diffusion Models
Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion ha...
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...
research
∙
05/19/2022
Automated Crossword Solving
We present the Berkeley Crossword Solver, a state-of-the-art approach fo...
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...
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...
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...
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...
research
∙
04/13/2021
Detoxifying Language Models Risks Marginalizing Minority Voices
Language models (LMs) must be both safe and equitable to be responsibly ...
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...
research
∙
12/14/2020
Extracting Training Data from Large Language Models
It has become common to publish large (billion parameter) language model...
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...
research
∙
10/23/2020
Customizing Triggers with Concealed Data Poisoning
Adversarial attacks alter NLP model predictions by perturbing test-time ...
research
∙
10/12/2020
Gradient-based Analysis of NLP Models is Manipulable
Gradient-based analysis methods, such as saliency map visualizations and...
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...
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 ...
research
∙
04/13/2020
Pretrained Transformers Improve Out-of-Distribution Robustness
Although pretrained Transformers such as BERT achieve high accuracy on i...
research
∙
04/06/2020
Evaluating NLP Models via Contrast Sets
Standard test sets for supervised learning evaluate in-distribution gene...
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...
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...
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...
research
∙
08/20/2019
Universal Adversarial Triggers for Attacking and Analyzing NLP
Adversarial examples highlight model vulnerabilities and are useful for ...
research
∙
08/20/2019
Universal Adversarial Triggers for NLP
Adversarial examples highlight model vulnerabilities and are useful for ...
research
∙
06/07/2019
Compositional Questions Do Not Necessitate Multi-hop Reasoning
Multi-hop reading comprehension (RC) questions are challenging because t...
research
∙
05/14/2019
Misleading Failures of Partial-input Baselines
Recent work establishes dataset difficulty and removes annotation artifa...
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...
research
∙
09/08/2018
Interpreting Neural Networks With Nearest Neighbors
Local model interpretation methods explain individual predictions by ass...
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...
research
∙
04/20/2018