arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.16403cs.CLcs.AI
收藏

基于适配器的知识增强语言模型方法——综述

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

Technical University of Munich(慕尼黑工业大学);SEBIS, Technical University of Munich(慕尼黑工业大学SEBIS)

Alexander Fichtl, Juraj Vladika, Georg Groh

AI总结:

本文系统综述了基于适配器的知识增强语言模型方法,分析现有方法优缺点,重点比较生物医学领域性能,并总结趋势与未来方向。

摘要:

知识增强语言模型(KELMs)已成为弥合大规模语言模型与领域特定知识之间差距的有前景的工具。通过利用知识图谱(KGs),KELMs 能够实现更高的事实准确性并缓解幻觉问题。它们经常与适配器模块结合,以降低计算负载和灾难性遗忘的风险。本文对基于适配器的 KELMs 方法进行了系统文献综述(SLR)。我们通过定量和定性分析,对该领域现有方法进行了结构化概述,并探讨了各种方法的优势与潜在不足。我们表明,通用知识和领域特定方法以及各种适配器架构和下游任务已被频繁探索。我们特别关注了流行的生物医学领域,并对现有 KELMs 进行了富有洞见的性能比较。我们概述了主要趋势并提出了有前景的未来方向。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑