3 papers
cs.CL2026
Re:CAP - Auditing Retrieval Coverage in Production RAG Pipelines
Aviral Joshi, Hanoz Bhathena, Max Nelson +1
Retrieval-augmented generation (RAG) is hard to monitor in production: exhaustive relevance labels do not exist for non-stationary multi-million-passage corpora that re-index in re…
cs.IR2026
Incremental Pooled LLM Evaluation for Cost-Effective Retrieval Model Selection
Max Nelson, Hanoz Bhathena, Aviral Joshi +1
Selecting a retrieval model for a production RAG system requires reliable comparative evaluation, but obtaining relevance judgments at scale is expensive and difficult to repeat as…
cs.CL2026
MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A
Hanoz Bhathena, Parin Rajesh Jhaveri, Rohan Mittal +7
Recent advances in multimodal retrieval-augmented generation (MM-RAG) have shifted toward minimal parsing, relying on page-level images for producing retriever embeddings and for a…