先思后链：多语言实体链接中的稀有性、推理与检索
原标题：Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking
AI 摘要
该论文研究多语言多模态实体链接中稀有实体的失败问题，指出传统基于流行度（如页面浏览量）的稀有度指标会遗漏许多知识图谱结构上稀疏的实体。作者提出用Wikidata结构指标刻画稀有度，并设计一个无需训练的框架，让具备推理能力的视觉语言模型迭代检索并推理Wikipedia证据。在MERLIN五语言基准上，最佳系统整体比SOTA提升6.9%，在稀有实体切片上最高提升23.3%，并发布MERLIN-Rare稀有实体测试切片。
正文节选
Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking Abstract Multimodal entity linking grounds entity mentions in text and images to knowledge-base entries. These systems degrade on rare entities, but prior work measures rarity primarily through popularity-based metrics such as pageviews. We broaden this view using knowledge-graph structural metrics that capture how well an entity is documented and connected. These metrics identify many rare entities that popul