RAG, Fine-Tuning & ContextZiyan Jiang et al. (University of Waterloo)
LongRAG published
LongRAG published — uses large retrieval units to lighten the retriever's load and hands them to a long-context reader
Why it matters
Treats RAG and long context not as rivals but as a redistribution of roles
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2406.15319Added in Week 35, 2026 · See that week