research
∙
05/23/2023
Skill-Based Few-Shot Selection for In-Context Learning
In-Context learning is the paradigm that adapts large language models to...
share
research
∙
05/08/2023
How Do In-Context Examples Affect Compositional Generalization?
Compositional generalization–understanding unseen combinations of seen p...
research
∙
02/23/2023
Does Deep Learning Learn to Abstract? A Systematic Probing Framework
Abstraction is a desirable capability for deep learning models, which me...
research
∙
03/07/2022
Input-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models
Recently the prompt-tuning paradigm has attracted significant attention....
research
∙
07/14/2021
Learning Algebraic Recombination for Compositional Generalization
Neural sequence models exhibit limited compositional generalization abil...
research
∙
06/18/2020