A structured multi-agent debate framework with domain-specialized AI agents and a five-dimension scoring rubric improves LLM-based fake news detection by several F1 points.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Models
A structured multi-agent debate framework with domain-specialized AI agents and a five-dimension scoring rubric improves LLM-based fake news detection by several F1 points.