Adversarial Contrastive Learning Sample Ratios and Cross-Lingual Rumor Detection Generalization

This report synthesises findings from 8 peer-reviewed papers addressing the following research question: How do different ratios of positive-to-negative samples in adversarial contrastive learning affect the generalizability of rumor detection models across languages, as evaluated by F1-score. 9 claims were extracted from source literature; 9 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How do different ratios of positive-to-negative samples in adversarial contrastive learning affect the generalizability of rumor detection models across languages, as evaluated by F1-score comparisons on the GLUE benchmark?

Autonomous literature synthesis. Automated review score: 8.2/10. Full text and citation available at Assignee Research.