Nov 10, 2023 Friday
Abstract:
Although large language models (LLMs) have achieved significant success in various tasks, they often struggle with hallucination problems, especially in scenarios requiring deep and responsible reasoning. These issues could be partially addressed by introducing external knowledge graphs (KG) in LLM reasoning. In this paper, we propose a new LLM-KG integrating paradigm “LLM⊗KG” which treats the LLM as an agent to interactively explore related entities and relations on KGs and perform reasoning based on the retrieved knowledge. We further implement this paradigm by introducing a new approach called Think-on-Graph (ToG), in which the LLM agent iteratively executes beam search on KG, discovers the most promising reasoning paths, and returns the most likely reasoning results. We use a number of well-designed experiments to examine and illustrate the following advantages of ToG: 1) compared with LLMs, ToG has better deep reasoning power; 2) ToG has the ability of knowledge traceability and knowledge correctability by leveraging LLMs reasoning and expert feedback; 3) ToG provides a flexible plug-and-play framework for different LLMs, KGs and prompting strategies without any additional training cost; 4) the performance of ToG with small LLM models could exceed large LLM such as GPT-4 in certain scenarios and this reduces the cost of LLM deployment and application. As a training-free method with lower computational cost and better generality, ToG achieves overall SOTA in 6 out of 9 datasets where most previous SOTAs rely on additional training.
Time:
Nov 10, 2023 Friday
11:00-11:50
Location:
RmE1-134, GZ Campus
Zoom:
628 334 1826 (PW: 234567)
Bilibili Live:
ID: 30748067
Speaker Bio:
Dr. Jian GUO
Executive President, IDEA
Chief Scientist of Al Finance and Deep Learning
Jian Guo is the Executive President of International Digital Economy Academy (IDEA) and the Chief Scientist of AI Finance and Deep Learning. He also serves as an adjunct professor of artificial intelligence at the Hong Kong University of Science and Technology (Guangzhou) and a professor of practice at Tsinghua University. Dr. Guo received his B.S. in mathematics from Tsinghua University in 2003, received his Ph.D. in Statistics from University of Michigan in 2011, and immediately started his professorship (tenure-track) at Harvard University. He published a number of research papers in methodology of statistical machine learning and deep learning, with applications in finance, internet and biomedicine. Dr. Guo is also an active researcher and a serial entrepreneur in next-generation quantitative investment technology with artificial intelligence.