research
∙
07/24/2023
Evaluating the Ripple Effects of Knowledge Editing in Language Models
Modern language models capture a large body of factual knowledge. Howeve...
share
research
∙
06/01/2023
The Hidden Language of Diffusion Models
Text-to-image diffusion models have demonstrated an unparalleled ability...
research
∙
05/22/2023
LM vs LM: Detecting Factual Errors via Cross Examination
A prominent weakness of modern language models (LMs) is their tendency t...
research
∙
04/28/2023
Dissecting Recall of Factual Associations in Auto-Regressive Language Models
Transformer-based language models (LMs) are known to capture factual kno...
research
∙
03/16/2023
Jump to Conclusions: Short-Cutting Transformers With Linear Transformations
Transformer-based language models (LMs) create hidden representations of...
research
∙
01/30/2023
Crawling the Internal Knowledge-Base of Language Models
Language models are trained on large volumes of text, and as a result th...
research
∙
10/07/2022
Understanding Transformer Memorization Recall Through Idioms
To produce accurate predictions, language models (LMs) must balance betw...
research
∙
09/06/2022
Analyzing Transformers in Embedding Space
Understanding Transformer-based models has attracted significant attenti...
research
∙
05/01/2022
Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions
In recent years, progress in NLU has been driven by benchmarks. These be...
research
∙
04/28/2022
Inferring Implicit Relations with Language Models
A prominent challenge for modern language understanding systems is the a...
research
∙
04/26/2022
LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models
The opaque nature and unexplained behavior of transformer-based language...
research
∙
03/28/2022
Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space
Transformer-based language models (LMs) are at the core of modern NLP, b...
research
∙
01/10/2022
SCROLLS: Standardized CompaRison Over Long Language Sequences
NLP benchmarks have largely focused on short texts, such as sentences an...
research
∙
07/29/2021
Break, Perturb, Build: Automatic Perturbation of Reasoning Paths through Question Decomposition
Recent efforts to create challenge benchmarks that test the abilities of...
research
∙
04/13/2021
What's in your Head? Emergent Behaviour in Multi-Task Transformer Models
The primary paradigm for multi-task training in natural language process...
research
∙
01/06/2021
Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies
A key limitation in current datasets for multi-hop reasoning is that the...
research
∙
12/29/2020
Transformer Feed-Forward Layers Are Key-Value Memories
Feed-forward layers constitute two-thirds of a transformer model's param...
research
∙
04/09/2020
Injecting Numerical Reasoning Skills into Language Models
Large pre-trained language models (LMs) are known to encode substantial ...
research
∙
01/31/2020
Break It Down: A Question Understanding Benchmark
Understanding natural language questions entails the ability to break do...
research
∙
08/21/2019
Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets
Crowdsourcing has been the prevalent paradigm for creating natural langu...
research
∙
02/27/2019
DiscoFuse: A Large-Scale Dataset for Discourse-based Sentence Fusion
Sentence fusion is the task of joining several independent sentences int...
research
∙
09/03/2018
Emergence of Communication in an Interactive World with Consistent Speakers
Training agents to communicate with one another given task-based supervi...
research
∙
06/09/2018
Learning to Search in Long Documents Using Document Structure
Reading comprehension models are based on recurrent neural networks that...
research
∙
07/14/2017