Adding more schema descriptions and examples to retrieved documents improves table retrieval but increases SQL query errors in a Text2SQL model, with the best balance at medium document richness.
Observations on Building RAG Systems for Technical Documents
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Retrieval augmented generation (RAG) for technical documents creates challenges as embeddings do not often capture domain information. We review prior art for important factors affecting RAG and perform experiments to highlight best practices and potential challenges to build RAG systems for technical documents.
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Balancing Content Size in RAG-Text2SQL System
Adding more schema descriptions and examples to retrieved documents improves table retrieval but increases SQL query errors in a Text2SQL model, with the best balance at medium document richness.