Skip to content

zrc0123/columbia-accenture-knowledge-graph-for-supply-chains

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

64 Commits
 
 
 
 

Repository files navigation

Columbia Accenture Knowledge Graph for Supply Chains

Team Member: Ruochen Zhang(rz2597), Yunjie Qian (yq2354), Weipeng Li (wl2864), Lingjun Zhang (lz2873), John Como (jtc2182)

The project aims to address the complex challenges in supply chain management and inventory decisions through the innovative solution, KnowledgeGraph+. By seamlessly integrating cutting-edge Large Language Models (LLMs) with Knowledge Graphs, the project aims to redefine efficiency and optimization in various industries.

4

Overall, we built a Q&A system leveraging the LLM's understanding of user queries and the extracted relevant content, personalized recommendations will be provided to the users.We also evaluated the level of hallucinations of different LLMs using triplets extracted from relevant content and answers,providing qualitative and quantitive analysis.

model

According to our research, adding a knowledge graph improves the quality of question answering with large language models by including more related information while reducing hallucination. Besides, larger models tend to have a lower level of hallucination. Further work will focus on optimizing the knowledge graph with more data to further improve the chatbot.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 99.6%
  • Python 0.4%