In this article, we evaluate the evolution of LLM capabilities w.r.t. the RDF Turtle and SPARQL language as foundational skills to assist with various KGE tasks. We measure the LLM response quality using 6 LLM-KG-Bench tasks for a total of 15 LLM versions available over the course of 2023, covering 5 different “major version” LLM classes (GPT-3.5 Turbo, GPT-4, Claude 1.x, Claude 2.x, and Claude Instant 1.x).

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Assessing the Evolution of LLM Capabilities for Knowledge Graph Engineering in 2023

  • Johannes Frey,
  • Lars-Peter Meyer,
  • Felix Brei,
  • Sabine Gründer-Fahrer,
  • Michael Martin

摘要

In this article, we evaluate the evolution of LLM capabilities w.r.t. the RDF Turtle and SPARQL language as foundational skills to assist with various KGE tasks. We measure the LLM response quality using 6 LLM-KG-Bench tasks for a total of 15 LLM versions available over the course of 2023, covering 5 different “major version” LLM classes (GPT-3.5 Turbo, GPT-4, Claude 1.x, Claude 2.x, and Claude Instant 1.x).