Parth Padalkar

NeSyFOLD: Neurosymbolic Framework for Interpretable Image Classification

2023 · arXiv (Cornell University)

Deep learning models such as CNNs have surpassed human performance in computer vision tasks such as image classification. However, despite their sophistication, these models lack interpretability which can lead to biased outcomes reflecting existing prejudices …

Reliable Natural Language Understanding with Large Language Models and Answer Set Programming

2023 · Electronic Proceedings in Theoretical Computer Science

Humans understand language by extracting information (meaning) from sentences, combining it with existing commonsense knowledge, and then performing reasoning to draw conclusions.While large language models (LLMs) such as GPT-3 and ChatGPT are able to leverage …