KGARevision: A Knowledge Graph-Based Agent for Medical AI Question Answering

KGARevision: A Knowledge Graph-Based Agent for Medical AI Question Answering

Discover AI via YouTube Direct link

Update LLM with grounded graph knowledge

8 of 13

8 of 13

Update LLM with grounded graph knowledge

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

KGARevision: A Knowledge Graph-Based Agent for Medical AI Question Answering

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Harvard has a problem w/ LLMs and RAG
  2. 2 Harvard Univ develops a new solution
  3. 3 The Generate Phase medical triplets
  4. 4 Review Phase of KGARevion
  5. 5 Multiple embeddings from LLM and Graphs
  6. 6 Alignment of all embeddings in common math space
  7. 7 Dynamic update of the Knowledge graph
  8. 8 Update LLM with grounded graph knowledge
  9. 9 Revise phase to correct incomplete triplets
  10. 10 Answer phase brings it all together
  11. 11 Summary
  12. 12 Performance analysis
  13. 13 All prompts for KGARevion in detail

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.