Towards Dependable Retrieval-Augmented Generation Using Factual Confidence Prediction

ArXi:2605.05244v1 Announce Type: cross Incorporating specific knowledge into large language models via retrieval-augmented generation (RAG) is a widespread technique that fuels many of today's industry AI applications. A fundamental problem is to assess if the context retrieved by some similarity search provides indeed ing facts, or instead misguides the generator with irrelevant information. It is critical to associate meaningful confidence measures about the factuality of the retrieval process with the generated answers.