We test the hypothesis that language models trained with reinforcement
l...
As AI systems become more capable, we would like to enlist their help to...
Developing safe and useful general-purpose AI systems will require us to...
"Induction heads" are attention heads that implement a simple algorithm ...
Neural networks often pack many unrelated concepts into a single neuron ...
Large Transformer models achieved the state-of-the-art status for Natura...
We describe our early efforts to red team language models in order to
si...
We study whether language models can evaluate the validity of their own
...
Recent large language models have been trained on vast datasets, but als...
We apply preference modeling and reinforcement learning from human feedb...
Large-scale pre-training has recently emerged as a technique for creatin...
Given the broad capabilities of large language models, it should be poss...
Statistical language modeling and translation with transformers have fou...
Pre-trained transformers have recently clinched top spots in the gamut o...
The joint task of bug localization and program repair is an integral par...
Detecting and fixing bugs are two of the most important yet frustrating ...
We approach the important challenge of code autocompletion as an open-do...
Simultaneously modeling source code and natural language has many exciti...
Pre-trained models for programming language have achieved dramatic empir...
Unit testing represents the foundational basis of the software testing
p...
Automated Unit Test Case generation has been the focus of extensive
lite...