The explosive growth of language models and their applications have led ...
Pretraining is the preliminary and fundamental step in developing capabl...
Foundation models pretrained on diverse data at scale have demonstrated
...
We study how in-context learning (ICL) in language models is affected by...
We study the design decisions of publicly available instruction tuning
m...
Large language models (LLMs) have demonstrated impressive capabilities i...
Although scaling language models improves performance on a range of task...
Scaling language models improves performance but comes with significant
...
Successful and effective communication between humans and AI relies on a...
We evaluate the reasoning abilities of large language models in multilin...
Recent research has shown that rationales, or step-by-step chains of tho...
We propose a novel prompting strategy, least-to-most prompting, that ena...
Large language models have been shown to achieve remarkable performance
...
We explore a simple ensemble strategy, self-consistency, that significan...
Although scaling up language model size has reliably improved performanc...
The classification of histopathology images fundamentally differs from
t...
Pre-trained language models perform well on a variety of linguistic task...
This paper asks whether extrapolating the hidden space distribution of t...
In this paper, we leverage large language models (LMs) to perform zero-s...
This paper explores a simple method for improving the zero-shot learning...
Although automated metrics are commonly used to evaluate NLG systems, th...
Generating context-aware language that embodies diverse emotions is an
i...
Experiments with pretrained models such as BERT are often based on a sin...
The uniform information density (UID) hypothesis, which posits that spea...
Current large-scale language models can be politically biased as a resul...
Few-shot text classification is a fundamental NLP task in which a model ...
With the rise of deep learning, there has been increased interest in usi...
Traditional data augmentation aims to increase the coverage of the input...
The field of NLP has seen unprecedented achievements in recent years. Mo...
Applying curriculum learning requires both a range of difficulty in data...
We present COVID-Q, a set of 1,690 questions about COVID-19 from 13 sour...
The unique nature of histopathology images opens the door to domain-spec...
We present an image translation approach to generate augmented data for
...
Deep learning for classification of microscopy images is challenging bec...