Niclas Hart, Nicolas Weeger · 2026 · arXiv
DOI: 10.48550/arXiv.2610.27816 · open-access PDF
Retrieval-Augmented Generation (RAG) se ha convertido en el paradigma dominante para fundamentar las salidas de los grandes modelos de lenguaje (LLM) en el conocimiento externo. Sin embargo, los practicantes se enfrentan a un amplio espacio de configuración que incluye chunking, embedding, retrieval, reranking, prompting y modelos de generación, y hay orientación limitada sobre cómo estos componentes interactúan. Presentamos RAG-NIMBF, un marco de referencia modular que se une a las tuberías RAG existentes como una capa de evaluación no invasiva. Evalúa el espacio de configuración a través de la ablación controlada con seguimiento experimental de fin a fin.
Machine translation (Meta M2M100); the English original follows.
Retrieval-Augmented Generation (RAG) has become the dominant paradigm for grounding the outputs of large language models (LLM) in external knowledge. However, practitioners are faced with a vast configuration space comprising chunking, embedding, retrieval, reranking, prompting and generation models, and there is limited guidance on how these components interact. We present RAG-NIMBF, a modular benchmarking framework that attaches to existing RAG pipelines as a non-invasive evaluation layer. It evaluates the configuration space through controlled ablation with end-to-end experiment tracking. T
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=2610.27816, 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