FACTUALITY

作品数：3被引量：0H指数：0
导出分析报告
相关领域：语言文字更多>>
相关期刊：《Science China(Information Sciences)》《Journal of Computer Science & Technology》《Computers, Materials & Continua》更多>>
-
在结果中检索

检索结果分析

结果分析中...
共 条 记 录，以下是1-3
全选清除导出
参考文献引证文献引用追踪
视图：
排序：
Document-Level Event Factuality Identification via Reinforced Semantic Learning Network
《Journal of Computer Science & Technology》2024年第6期1248-1268,共21页Zhong Qian Pei-Feng Li Qiao-Ming Zhu Guo-Dong Zhou 
supported by the National Natural Science Foundation of China under Grant Nos.62006167,62276177,62376181,and 62376178;the Natural Science Foundation of the Jiangsu Higher Education Institutions of China under Grant No.24KJB520036;the Project Funded by the Priority Academic Program Development(PAPD)of Jiangsu Higher Education Institutions.
This paper focuses on document-level event factuality identification (DEFI), which predicts the factual nature of an event from the view of a document. As the document-level sub-task of event factuality identification...
关键词：document-level event factuality identification hierarchical reinforcement learning attention network multi-granularity encoding 
A News Media Bias and Factuality Profiling Framework Assisted by Modeling Correlation
《Computers, Materials & Continua》2024年第11期3351-3369,共19页Qi Wang Chenxin Li Chichen Lin Weijian Fan Shuang Feng Yuanzhong Wang 
funded by“the Fundamental Research Funds for the Central Universities”,No.CUC23ZDTJ005.
News media profiling is helpful in preventing the spread of fake news at the source and maintaining a good media and news ecosystem.Most previous works only extract features and evaluate media from one dimension indep...
关键词：News media profiling FACTUALITY BIAS correlated features 
Unveiling factuality and injecting knowledge for LLMs via reinforcement learning and data proportion
《Science China(Information Sciences)》2024年第10期385-386,共2页Wenjun KE Ziyu SHANG Zhizhao LUO Peng WANG Yikai GUO Qi LIU Yuxuan CHEN 
supported by the National Science Foundation of China (Grant No. 62376057)。
Large language models(LLMs) have demonstrated remarkable effectiveness across various natural language processing(NLP) tasks, as evidenced by recent studies [1, 2]. However, these models often produce responses that c...
关键词：KNOWLEDGE learning CRITICAL 
全选清除导出
共1页<1>
检索报告 对象比较 聚类工具 使用帮助 返回顶部