The methodology must achieve alignment between LLM token embeddings (from the language model's understanding of text) and knowledge graph structural embeddings (from graph theory), by adding a projection layer that transforms the dimensionality and structure of LLM embeddings to match knowledge graph embeddings, creating a shared geometric space where both types of knowledge can be combined.

factualpending

Speaker

Unidentified Speaker — Harvard Presents NEW Knowledge-Graph AGENT (MedAI) [Fm68I-phaiY]

Evidence Quote

“we simply add a projection layer for example now we do this on the token embeddings which will adjust their dimensionality and their structure to match here the format of the knowledge graph embeddings”

Source

Harvard Presents NEW Knowledge-Graph AGENT (MedAI)— Discover AI
Created: 8/10/2026, 10:46:21 PM

Your notes

Loading notes...