SALF uses adversarial LLM prompt-refinement and debate to make fake news harder to detect (detector F1 drops up to 53% in Chinese, 34% in English) while its oracle-informed detector improves by 7.7%.
The goal is to increase credibility and make it more resistant to scrutiny, while keeping the text fictional
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
-
A Symbolic Adversarial Learning Framework for Evolving Fake News Generation and Detection
SALF uses adversarial LLM prompt-refinement and debate to make fake news harder to detect (detector F1 drops up to 53% in Chinese, 34% in English) while its oracle-informed detector improves by 7.7%.