Blog: hmfodg

Each argument has its own map of routes that changes depending on the order in which and with what you connect it. Read more…

In the Hierarchical Metric Flow on Data Graphs (HMFoDG) implementation, an interesting analytical feature emerged. It enables auditing of RAG systems (and embeddings or any vectorized data - biotech, medical, finance, physics, etc.) by tracing the selected associations in a deterministic way (without heuristics). This means deterministically tracking what the transformer actually used during the reinforcement process that caused one token to lie close to another. These are very concrete references (e.g., author, specific tokens from the text that in sufficient quantity allow source identification). Read more…