Pretrained large language models (LLMs) are able to solve a wide variety...
Text-based safety classifiers are widely used for content moderation and...
Recent developments in natural language generation (NLG) using neural
la...
Prior work has explored the writing challenges experienced by people wit...
The task of inserting text into a specified position in a passage, known...
NLP researchers need more, higher-quality text datasets. Human-labeled
d...
The intensification of affective polarization worldwide has raised new
q...
In this paper, we leverage large language models (LMs) to perform zero-s...
As neural language models grow in effectiveness, they are increasingly b...
We describe an "interpretability illusion" that arises when analyzing th...
We present the Language Interpretability Tool (LIT), an open-source plat...
Transformer architectures show significant promise for natural language
...
TensorFlow.js is a library for building and executing machine learning
a...
Homophily --- our tendency to surround ourselves with others who share o...