{"ID":2860732,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.02657","arxiv_id":"2510.02657","title":"Less LLM, More Documents: Searching for Improved RAG","abstract":"Retrieval-Augmented Generation (RAG) couples document retrieval with large language models (LLMs). While scaling generators often improves accuracy, it also increases inference and deployment overhead. We study an orthogonal axis: enlarging the retriever's corpus, and how it trades off with generator scale. Across multiple open-domain QA benchmarks, corpus scaling consistently strengthens RAG and can in many cases match the gains of moving to a larger model tier, though with diminishing returns at larger scales. Small- and mid-sized generators paired with larger corpora often rival much larger models with smaller corpora; mid-sized models tend to gain the most, while tiny and very large models benefit less. Our analysis suggests that these improvements arise primarily from increased coverage of answer-bearing passages, while utilization efficiency remains largely unchanged. Overall, our results characterize a corpus-generator trade-off in RAG and provide empirical guidance on how corpus scale and model capacity interact in this setting.","short_abstract":"Retrieval-Augmented Generation (RAG) couples document retrieval with large language models (LLMs). While scaling generators often improves accuracy, it also increases inference and deployment overhead. We study an orthogonal axis: enlarging the retriever's corpus, and how it trades off with generator scale. Across mult...","url_abs":"https://arxiv.org/abs/2510.02657","url_pdf":"https://arxiv.org/pdf/2510.02657v3","authors":"[\"Jingjie Ning\",\"Yibo Kong\",\"Yunfan Long\",\"Jamie Callan\"]","published":"2025-10-03T01:26:13Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.CL\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false}