Structure-Guided Entity Resolution: Fine-Tuning LLMs for Robust Name Matching in Complex Linguistic Contexts
结构引导的实体解析:微调大语言模型以实现复杂语言上下文中的鲁棒姓名匹配
机构 * Dream Sports
专题命中 指令微调 :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)
AI总结 提出结构引导实体解析(SGER)框架,通过两阶段课程微调大语言模型,先学习姓名语法结构再优化匹配任务,在印度身份数据上达到99.02%准确率和0.994 F1分数,已部署于Dream11平台服务2.5亿+用户。
Comments Accepted to ACL 2026. 8 pages, 1 figure, 2 tables
Journal ref Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track), pages 1461-1468, 2026