利用LLM生成解释检测情感改写假新闻

1. 12:00
   arXiv · Computation and Language

   利用 LLM 生成的解释检测情感改写后的假新闻

   该研究针对保留事实但被情感改写的新闻，构建了情感改写测试集，并以原新闻生成的解释作为稳定背景知识。研究提出 Gated Cross Attention（GCA）框架，自适应融合改写新闻与解释，减少情感重构带来的不匹配。

Current heat 9·Comparable peak 10（Oct 8）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.