Scaling up Discovery of Latent Concepts in Deep NLP Models

Majd Hawasly, Fahim Dalvi, Nadir Durrani

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Despite the revolution caused by deep NLP models, they remain black boxes, necessitating research to understand their decision-making processes. A recent work by Dalvi et al. (2022) carried out representation analysis through the lens of clustering latent spaces within pretrained models (PLMs), but that approach is limited to small scale due to the high cost of running Agglomerative hierarchical clustering. This paper studies clustering algorithms in order to scale the discovery of encoded concepts in PLM representations to larger datasets and models. We propose metrics for assessing the quality of discovered latent concepts and use them to compare the studied clustering algorithms. We found that K-Means-based concept discovery significantly enhances efficiency while maintaining the quality of the obtained concepts. Furthermore, we demonstrate the practicality of this newfound efficiency by scaling latent concept discovery to LLMs and phrasal concepts.

Original languageEnglish
Title of host publicationEACL 2024 - 18th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
EditorsYvette Graham, Matthew Purver, Matthew Purver
PublisherAssociation for Computational Linguistics (ACL)
Pages793-806
Number of pages14
ISBN (Electronic)9798891760882
Publication statusPublished - 22 Mar 2024
Event18th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2024 - St. Julian's, Malta
Duration: 17 Mar 202422 Mar 2024

Publication series

NameEACL 2024 - 18th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
Volume1

Conference

Conference18th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2024
Country/TerritoryMalta
CitySt. Julian's
Period17/03/2422/03/24

Fingerprint

Dive into the research topics of 'Scaling up Discovery of Latent Concepts in Deep NLP Models'. Together they form a unique fingerprint.

Cite this