Skip to content
arXiv cs.CL · Papers

Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation

arXiv:2601.11443v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) has emerged as a powerful approach for enhancing large language models' question-answering capabilities through the integration of external knowledge. However, when adapting RAG systems to specialized domains, challenges arise from