Search Results for author:
Found 4 papers, 1 papers with code
CoDa: Constrained Generation based Data Augmentation for Low-Resource NLP
We present CoDa (Constrained Generation based Data Augmentation), a controllable, effective, and training-free data augmentation technique for low-resource (data-scarce) NLP.
A Closer Look at the Limitations of Instruction Tuning
Our findings reveal that responses generated solely from pre-trained knowledge consistently outperform responses by models that learn any form of new knowledge from IT on open-source datasets.
RECAP: Retrieval-Augmented Audio Captioning
We present RECAP (REtrieval-Augmented Audio CAPtioning), a novel and effective audio captioning system that generates captions conditioned on an input audio and other captions similar to the audio retrieved from a datastore.
ASPIRE: Language-Guided Augmentation for Robust Image Classification
This paper presents ASPIRE (Language-guided data Augmentation for SPurIous correlation REmoval), a simple yet effective solution for expanding the training dataset with synthetic images without spurious features.
