MAPLE：多角度全文科学论文检索基准
原标题：Can Retrievers Find the Same Paper from Different Aspects? A Multi-Aspect Full-Paper Scientific Retrieval Benchmark
AI 摘要
研究人员提出了MAPLE基准，用于评估检索器能否从多个方面（如动机、方法和实验结果）一致地检索同一篇科学论文。MAPLE包含2095个查询，涉及210篇近期机器学习和NLP论文，并提出了MAPLE-Synth流水线来生成逼真的查询。实验表明，最强模型在AnyAspect@20上达到98.1%，但在AllAspect@20上仅为15.7%，揭示了多角度检索的显著差距。
正文节选
Can Retrievers Find the Same Paper from Different Aspects? A Multi-Aspect Full-Paper Scientific Retrieval Benchmark Abstract. Scientific papers contain multiple searchable facets such as background, methods. However, many paper retrieval benchmarks merely evaluate individual query-paper relevance, while overlooking other facets of the same paper. To bridge this gap, we introduce MAPLE, an expert-validated benchmark for multi-aspect, full-paper retrieval that evaluates whether retrievers can con