"YpathRAG Benchmark: Reranking and QA Evaluation Data for Pathology Evidence Retrieval"
Abstract
"This dataset provides benchmark data for evaluating the YpathRAG framework, a supportiveness-aware evidence retrieval and reranking system designed for pathology question answering. It contains three components: (1) a reranking benchmark with evaluation queries annotated with supportive and non-supportive passage labels, enabling the assessment of reranking models on distinguishing answer-justifying evidence from topically related but non-supportive passages; (2) a downstream pathology question-answering evaluation set with per-question metrics for measuring end-to-end QA performance under different retrieval configurations; and (3) ablation study data comprising top-30 retrieval candidates from both dense-only (BGE) and hybrid (dense + lexicon-guided sparse) pipelines in JSONL format, facilitating reproduction of comparative experiments. All data are derived from a 1.53-million-passage Chinese pathology corpus. The dataset supports research in biomedical information retrieval, evidence-based question answering, and retrieval-augmented generation for clinical NLP applications."
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.