Scholarlink

This study explores the use of Large Language Models (LLMs) for Claim Check-Worthiness Prediction (CCWP), a crucial pre-screening task in fact-checking. We predict the time between a claim’s occurrence and verification by analyzing data from fact-checking organizations. The results show that validation time is the same between the top 25% and bottom 75% of total checklist condition fulfillment claims. That is, further optimization is needed for LLMs to perform effective CCWPs.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Feature Extraction for Claim Check-Worthiness Prediction Tasks Using LLM

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Yuka Teramoto,
  • Takahiro Komamizu,
  • Mitsunori Matsushita,
  • Kenji Hatano

摘要

This study explores the use of Large Language Models (LLMs) for Claim Check-Worthiness Prediction (CCWP), a crucial pre-screening task in fact-checking. We predict the time between a claim’s occurrence and verification by analyzing data from fact-checking organizations. The results show that validation time is the same between the top 25% and bottom 75% of total checklist condition fulfillment claims. That is, further optimization is needed for LLMs to perform effective CCWPs.