@inproceedings{bb84414da4744f9882f7f20079287e7c,
title = "ConceptX: A Framework for Latent Concept Analysis",
abstract = "The opacity of deep neural networks remains a challenge in deploying solutions where explanation is as important as precision. We present ConceptX, a human-in-the-loop framework for interpreting and annotating latent representational space in pre-trained Language Models (pLMs). We use an unsupervised method to discover concepts learned in these models and enable a graphical interface for humans to generate explanations for the concepts. To facilitate the process, we provide auto-annotations of the concepts (based on traditional linguistic ontologies). Such annotations enable development of a linguistic resource that directly represents latent concepts learned within deep NLP models. These include not just traditional linguistic concepts, but also task-specific or sensitive concepts (words grouped based on gender or religious connotation) that helps the annotators to mark bias in the model. The framework consists of two parts (i) concept discovery and (ii) annotation platform.",
author = "Firoj Alam and Fahim Dalvi and Nadir Durrani and Hassan Sajjad and Khan, {Abdul Rafae} and Jia Xu",
note = "Publisher Copyright: Copyright {\textcopyright} 2023, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.; 37th AAAI Conference on Artificial Intelligence, AAAI 2023 ; Conference date: 07-02-2023 Through 14-02-2023",
year = "2023",
month = jun,
day = "27",
doi = "10.1609/aaai.v37i13.27057",
language = "English",
series = "Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023",
publisher = "AAAI Press",
pages = "16395--16397",
editor = "Brian Williams and Yiling Chen and Jennifer Neville",
booktitle = "AAAI-23 Special Programs, IAAI-23, EAAI-23, Student Papers and Demonstrations",
}