Knowledge Base
Knowledge bases (KBs) are structured repositories of factual information, increasingly utilized to enhance the capabilities of large language models (LLMs). Current research focuses on integrating LLMs with KBs, improving knowledge retrieval and reasoning, and addressing challenges like hallucination and bias through techniques such as knowledge graph embeddings, retrieval-augmented generation (RAG), and fine-tuning. This work is significant because reliable and comprehensive KBs are crucial for building trustworthy and accurate AI systems, with applications ranging from question answering and information retrieval to supporting decision-making in various domains.
Papers
KB-Plugin: A Plug-and-play Framework for Large Language Models to Induce Programs over Low-resourced Knowledge Bases
Jiajie Zhang, Shulin Cao, Linmei Hu, Ling Feng, Lei Hou, Juanzi Li
The Queen of England is not England's Queen: On the Lack of Factual Coherency in PLMs
Paul Youssef, Jörg Schlötterer, Christin Seifert