Long-Context LLMs Meet RAG
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
finds that for many long-context LLMs, the quality of outputs declines as the number of passages increases; reports that the performance loss is due to retrieved hard negatives; they propose two ways to improve long-context LLM-based RAG: retrieval reordering and RAG-specific tuning with intermediate reasoning to help with relevance identification; that approaches demonstrate significant accuracy and robustness improvements on long-context RAG performance.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack