Towards Concept-Aware Large Language Models

Chen Shani, Jilles Vreeken, Dafna Shahaf


Abstract
Concepts play a pivotal role in various human cognitive functions, including learning, reasoning and communication. However, there is very little work on endowing machines with the ability to form and reason with concepts. In particular, state-of-the-art large language models (LLMs) work at the level of tokens, not concepts. In this work, we analyze how well contemporary LLMs capture human concepts and their structure. We then discuss ways to develop concept-aware LLMs, taking place at different stages of the pipeline. We sketch a method for pretraining LLMs using concepts, and also explore the simpler approach that uses the output of existing LLMs. Despite its simplicity, our proof-of-concept is shown to better match human intuition, as well as improve the robustness of predictions. These preliminary results underscore the promise of concept-aware LLMs.
Anthology ID:
2023.findings-emnlp.877
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13158–13170
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.877
DOI:
10.18653/v1/2023.findings-emnlp.877
Bibkey:
Cite (ACL):
Chen Shani, Jilles Vreeken, and Dafna Shahaf. 2023. Towards Concept-Aware Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 13158–13170, Singapore. Association for Computational Linguistics.
Cite (Informal):
Towards Concept-Aware Large Language Models (Shani et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/2023.findings-emnlp.877.pdf
Video:
 https://preview.aclanthology.org/naacl-24-ws-corrections/2023.findings-emnlp.877.mp4