AI RESEARCH
Separating Semantic Competition from Context Length in RAG Reading
arXiv CS.CL
•
ArXi:2605.27294v1 Announce Type: new Retrieval-augmented generation (RAG) systems can respond incorrectly even when the correct passage was retrieved. The model must still read the retrieved passages and identify which one contains the answer among others that look relevant. This passage-reading model is called the reader. Does it fail simply because the context is longer or because the other passages genuinely compete with the correct one? We