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
Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Database
Ye Liu, Semih Yavuz, Rui Meng, Dragomir Radev, Caiming Xiong, Yingbo Zhou
Evident: a Development Methodology and a Knowledge Base Topology for Data Mining, Machine Learning and General Knowledge Management
Mingwu, Gao, Samer Haidar