Ido Levy, Segev Shlomov, Leshem Choshen · 2026 · arXiv
DOI: 10.48550/arXiv.2610.29722 · open-access PDF
Retrieval Augmented Generation (RAG) 基于外部知识的大型语言模型. 现代管道结合嵌入,切割,检索,重新排列,查询扩展,背景压缩和代理验证,但这些技术通常一次性地评估一次。 仍然不清楚它们的孤立收益是否存活在构成中,检索质量和响应忠诚性是否有利于相同的设计选择,以及小型企业的结论是否大规模。
Machine translation (Meta M2M100); the English original follows.
Retrieval Augmented Generation (RAG) grounds large language models in external knowledge. Modern pipelines combine embedding, chunking, retrieval, reranking, query augmentation, context compression, and agentic verification, yet these techniques are typically evaluated one at a time. It remains unclear whether their isolated gains survive composition, whether retrieval quality and answer faithfulness favor the same design choices, and whether conclusions from small corpora hold at large scale. We pre-declare three hypotheses and introduce LASAGNA, an open-source framework for controlled RAG ev
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29722, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange