In the extraction pipeline, Graffiti tries hard to avoid using LLMs where possible, instead deploying traditional information retrieval and NLP techniques (entropy analysis, simhashing for deduplication) because these are far cheaper, faster, and more deterministic than LLM-based approaches.

normativepending

Speaker

Daniel Ursell

Evidence Quote

“A lot of what we do uses LLMs but we try very hard not to use LLMs in this process as well. So where we're able to deploy more traditional information retrieval techniques, more traditional NLP techniques, uh looking at things like entropy and a bunch of other, you know, using um sim hash and a bunch of other approaches to ddupe, uh we do so uh far cheaper, far faster, deter more more far more deterministic.”

Source

Citation Needed: Provenance for LLM-Built Knowledge Graphs — Daniel Chalef, Zep AI— AI Engineer
Created: 8/12/2026, 5:58:29 PM

Your notes

Loading notes...