Search Results for author:
Found 2 papers, 2 papers with code
Program Synthesis with Large Language Models
Our largest models, even without finetuning on a code dataset, can synthesize solutions to 59. 6 percent of the problems from MBPP using few-shot learning with a well-designed prompt.
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
The interpretation of deep learning models is a challenge due to their size, complexity, and often opaque internal state.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
