Diagnosing and Repairing Factual Errors in RAG under Budget Constraints

Soroush Hashemifar, Havva Alizadeh Noughabi, Fattane Zarrinkalam +1

Retrieval-Augmented Generation (RAG) improves the factuality of large language models by grounding responses in external evidence, yet real-world deployments remain fragile. Failur…