Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications
This is an incremental survey that synthesizes existing research for the AI and NLP communities, aiming to facilitate access and guide future work in knowledge-enhanced LLMs.
This paper addresses the lack of a comprehensive survey on integrating external knowledge into large language models (LLMs) to mitigate issues like outdated data and domain-specific limitations, providing a taxonomy of methods, benchmarks, and applications to offer a quick overview and inspire future research.
Large language models (LLMs) exhibit superior performance on various natural language tasks, but they are susceptible to issues stemming from outdated data and domain-specific limitations. In order to address these challenges, researchers have pursued two primary strategies, knowledge editing and retrieval augmentation, to enhance LLMs by incorporating external information from different aspects. Nevertheless, there is still a notable absence of a comprehensive survey. In this paper, we propose a review to discuss the trends in integration of knowledge and large language models, including taxonomy of methods, benchmarks, and applications. In addition, we conduct an in-depth analysis of different methods and point out potential research directions in the future. We hope this survey offers the community quick access and a comprehensive overview of this research area, with the intention of inspiring future research endeavors.