Adapter-Based Approaches to Knowledge-Enhanced Language Models: A Survey

Alexander Fichtl, Juraj Vladika, Georg Groh

2024

Abstract

Knowledge-enhanced language models (KELMs) have emerged as promising tools to bridge the gap between large-scale language models and domain-specific knowledge. KELMs can achieve higher factual accuracy and mitigate hallucinations by leveraging knowledge graphs (KGs). They are frequently combined with adapter modules to reduce the computational load and risk of catastrophic forgetting. In this paper, we conduct a systematic literature review (SLR) on adapter-based approaches to KELMs. We provide a structured overview of existing methodologies in the field through quantitative and qualitative analysis and explore the strengths and potential shortcomings of individual approaches. We show that general knowledge and domain-specific approaches have been frequently explored along with various adapter architectures and downstream tasks. We particularly focused on the popular biomedical domain, where we provided an insightful performance comparison of existing KELMs. We outline the main trends and propose promising future directions.

Paper Citation

in Harvard Style

Fichtl A., Vladika J. and Groh G. (2024). Adapter-Based Approaches to Knowledge-Enhanced Language Models: A Survey. In Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 2: KEOD; ISBN 978-989-758-716-0, SciTePress, pages 95-107. DOI: 10.5220/0013058500003838

in Bibtex Style

@conference{keod24,
author={Alexander Fichtl and Juraj Vladika and Georg Groh},
title={Adapter-Based Approaches to Knowledge-Enhanced Language Models: A Survey},
booktitle={Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 2: KEOD},
year={2024},
pages={95-107},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013058500003838},
isbn={978-989-758-716-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 2: KEOD
TI - Adapter-Based Approaches to Knowledge-Enhanced Language Models: A Survey
SN - 978-989-758-716-0
AU - Fichtl A.
AU - Vladika J.
AU - Groh G.
PY - 2024
SP - 95
EP - 107
DO - 10.5220/0013058500003838
PB - SciTePress