Miguel Mochizuki Silva, Samuel Ismael, Mateus C. Dias, Thaís Gaudêncio, Yuri Malheiros, Barufaldi · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31606 · open-access PDF
Propósito: Describir un protocolo de evaluación de recuperación consciente de la evidencia para un sistema de generación aumentada de recuperación clínica (RAG) sobre la literatura de gestión de lesiones mamarias, abordando la dependencia de las puntuaciones de recuperación en la cobertura de la anotación. Métodos: Se utilizaron un corpus de documentos de 18 y un benchmark de desarrollo de preguntas de 18 con una pregunta Sí/No o WH por documento. Se utilizaron las combinaciones de incorporación densa, BM25 y reorganización de codificadores cruzados. Se evaluaron los tamaños de 128 a 1024 tokens, las superposiciones de 0 a 20%, y se determinaron cuatro configuraciones de retriever.
Machine translation (Meta M2M100); the English original follows.
Purpose: To describe an evidence-aware retrieval evaluation protocol for a clinical retrieval-augmented generation (RAG) system over breast lesion management literature, addressing the dependence of retrieval scores on annotation coverage. Methods: An 18-document corpus and an 18-query development benchmark, with one Yes/No or WH-question per document, were used. Retrieval combined dense embeddings, BM25, and cross-encoder reranking. Chunk sizes of 128 to 1024 tokens, overlaps of 0 to 20%, and four retriever configurations were evaluated. Relevance was defined by evidence spans mapped to all c
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=2610.31606, 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