RADAR: Retrieval-Augmented Detector with Adversarial Refinement for Adaptive LLM-Generated Fake News Detection

arXiv:2601.03981 · cs.CL · Submitted 2026-01-07 · Read on arXiv

cs.CL

Submitted: 2026-01-07

Updated: 2026-09-20

Comments: Accepted at WOAH 2026, co-located with EMNLP 2026

License: http://creativecommons.org/licenses/by/4.0/

The gist: To efficiently combat the spread of LLM-generated misinformation in the news domain, we present RADAR, a Retrieval-Augmented Detector with Adversarial Refinement for adaptive LLM-generated fake news

Terminology

Abstract

To efficiently combat the spread of LLM-generated misinformation in the news domain, we present RADAR, a Retrieval-Augmented Detector with Adversarial Refinement for adaptive LLM-generated fake news detection. Our approach employs a generator that rewrites real articles with factual perturbations, paired with a lightweight detector that verifies claims using dense passage retrieval. To enable effective co-evolution, we introduce Verbal Adversarial Feedback (VAF). Rather than relying on scalar rewards, VAF issues structured natural-language critiques; these guide the generator toward more sophisticated evasion attempts, compelling the detector to adapt and improve. Experiments on an LLM-generated fake news benchmark show that RADAR outperforms retrieval-augmented trainable baselines and general-purpose LLMs with retrieval. Further analysis shows that retrieval on both the generator and detector sides improves performance, while VAF and few-shot demonstrations offer complementary benefits. RADAR also transfers better to fake news generated by an unseen external attacker, suggesting improved generalization beyond the specific co-evolved generator used during training.

Sources

Related papers