New benchmarks mamabench and mamaretrieval released for medical RAG

By PulseAugur Editorial · [1 sources] · 2026-06-28 15:51

Researchers have introduced two new benchmarks, mamabench and mamaretrieval, designed to evaluate retrieval-augmented generation (RAG) systems specifically for maternal, neonatal, and reproductive health. These benchmarks address a gap in existing medical QA datasets by focusing on the unique questions faced by healthcare professionals in this domain. mamabench includes a large question-answering set and a re-scoped version of HealthBench for LLM judge calibration, while mamaretrieval provides detailed relevance labels for a corpus of maternal health guidelines. AI

IMPACT These benchmarks will enable more accurate evaluation of AI systems in specialized medical fields, potentially improving clinical decision support.

RANK_REASON The cluster contains a research paper introducing new benchmarks for a specific domain. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.IR (Information Retrieval) →

paper
other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New benchmarks mamabench and mamaretrieval released for medical RAG

COVERAGE [1]

arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Yi Ren · 2026-06-28 15:51

mamabench and mamaretrieval: Benchmarks for Evaluating Medical Retrieval-Augmented Generation in Maternal, Neonatal, and Reproductive Health

Medical question-answering benchmarks rarely cover the maternal, neonatal, child, and reproductive-health questions a nurse-midwife asks, and, to our knowledge, no public chunk-level relevance benchmark exists for maternal-health guideline retrieval. We release two benchmarks tha…

COVERAGE [1]

mamabench and mamaretrieval: Benchmarks for Evaluating Medical Retrieval-Augmented Generation in Maternal, Neonatal, and Reproductive Health

RELATED ENTITIES

RELATED TOPICS