Adapter-based Approaches to Knowledge-enhanced Language Models -- A Survey

TL;DR

This survey reviews adapter-based methods for knowledge-enhanced language models, highlighting their architectures, applications, and performance, especially in biomedical domains, and discusses future research directions.

Contribution

It provides a comprehensive systematic literature review of adapter-based KELMs, analyzing methodologies, strengths, limitations, and domain-specific applications, particularly in biomedicine.

Findings

Knowledge and domain-specific approaches are prevalent.

Various adapter architectures are used across tasks.

Biomedical KELMs show promising performance.

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.