Using a taxonomy to make banking document search cheaper
A banking RAG system for legal and finance documents can improve BM25 search by using a taxonomy and during . One option keeps the original document text and adds standard concept names and synonyms to the index.
For example, if a document says “ABS,” the index can also include “asset-backed securities,” so both forms can find the same document. Another option indexes only terms that exist in the legal taxonomy or , instead of every word.
That may reduce noisy matches, but it can also miss important wording that is not covered by the taxonomy. A is also being built, but the immediate issue is how to improve document .
Key points
- The use case is a banking RAG system for legal and finance documents.
- One approach adds standard concept names and synonyms to the index while keeping the original text searchable.
- Another approach indexes only taxonomy or terms to reduce noise.
- Better can reduce unnecessary context and lower for .
- only approved terms may miss useful documents if the taxonomy is incomplete.