Observations on Building RAG Systems for Technical Documents

Sujoy Roychowdhury; Sumit Soman

Observations on Building RAG Systems for Technical Documents

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.00657 v1 pith:Q3L46H6V submitted 2024-03-31 cs.LG cs.AIcs.CL

Sumit Soman , Sujoy Roychowdhury This is my paper · ORCID

classification cs.LGcs.AIcs.CL

keywords documentstechnicalchallengessystemsaffectingaugmentedbestbuild

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

Balancing Content Size in RAG-Text2SQL System
cs.IR 2025-01 conditional novelty 4.0 of 10

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.

Pith tools