Key points are not available for this paper at this time.
Retrieval-augmented generation (RAG) greatly benefits language models (LMs) by providing additional context for tasks such as document-based question answering (DBQA). Despite its potential, the power of RAG is highly dependent on its configuration, raising the question: What is the optimal RAG configuration? To answer this, we introduce the RAGGED framework to analyze and optimize RAG systems. On a set of representative DBQA tasks, we study two classic sparse and dense retrievers, and four top-performing LMs in encoder-decoder and decoder-only architectures. Through RAGGED, we uncover that different models suit substantially varied RAG setups. While encoder-decoder models monotonically improve with more documents, we find decoder-only models can only effectively use < 5 documents, despite often having a longer context window. RAGGED offers further insights into LMs' context utilization habits, where we find that encoder-decoder models rely more on contexts and are thus more sensitive to retrieval quality, while decoder-only models tend to rely on knowledge memorized during training.
Building similarity graph...
Analyzing shared references across papers
Loading...
Hsia et al. (Wed,) studied this question.
www.synapsesocial.com/papers/68e74464b6db6435876be1ba — DOI: https://doi.org/10.48550/arxiv.2403.09040
Jennifer Hsia
Afreen Shaikh
Zhiruo Wang
Building similarity graph...
Analyzing shared references across papers
Loading...