| 标题 |
 Collaborate SLM and LLM with latent answers for event detection 使用潜在答案协作SLM和LLM进行事件检测
相关领域
事件（粒子物理）
计算机科学
心理学
物理
量子力学
|
| 网址 | |
| DOI | |
| 其它 |
Abstract Event detection (ED) intends to identify events from text and classify them into predefined event types. One of the major issues for ED is the low-resource problem due to inadequate samples. Some studies address the low-resource issue with retrieving knowledge entries directly from knowledge bases while introducing a lot of irrelevant knowledge or failing the lookup. Moreover, recent work has attempted to employ large language models (LLMs, e.g., ChatGPT) that directly access event types in unstructured text under low-resource scenarios. Although LLM-based approaches have obtained promising results, we consider that the full potential of LLMs has not been activated due to insufficient prompt information. |
| 求助人 | |
| 下载 | 该求助完结已超 24 小时，文件已从服务器自动删除，无法下载。 |
|
温馨提示：该文献已被科研通 学术中心 收录，前往查看
科研通『学术中心』是文献索引库，收集文献的基本信息（如标题、摘要、期刊、作者、被引量等），不提供下载功能。如需下载文献全文，请通过文献求助获取。
|
PDF的下载单位、IP信息已删除
(2025-6-4)
GingerF
辛勤冬天
学术文献互助
1111
YifanWang
Willa
AllRightReserved
无极微光
贪玩的秋柔
MP
初景
ZeKaWa
Nature
Jiaxin
Rita
Belikov
干净的琦
嘉心糖
ccm
情怀
皖公网安备34019202002308
