Adapter-based Approaches to Knowledge-enhanced Language Models -- A Survey
It provides a systematic review for researchers working on integrating knowledge into language models, but it is incremental as it summarizes existing work.
This paper surveys adapter-based approaches to knowledge-enhanced language models (KELMs), analyzing methodologies and comparing performance, particularly in the biomedical domain, to outline trends and future directions.
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.