Real-time Factuality Assessment from Adversarial Feedback

TL;DR

This paper introduces a new evaluation method for factuality in news detection that uses adversarial feedback and retrieval-augmented generation to create challenging deceptive news variants, exposing vulnerabilities in current detectors.

Contribution

It proposes a novel pipeline leveraging RAG-based feedback to generate adversarial news examples, improving the robustness of factuality assessments for real-time news detection.

Findings

Iterative rewriting reduces detector ROC-AUC by 17.5%

RAG-based feedback enhances detection of deceptive news

Retrieval-free detectors are vulnerable to unseen events

Abstract

We show that existing evaluations for assessing the factuality of news from conventional sources, such as claims on fact-checking websites, result in high accuracies over time for LLM-based detectors-even after their knowledge cutoffs. This suggests that recent popular false information from such sources can be easily identified due to its likely presence in pre-training/retrieval corpora or the emergence of salient, yet shallow, patterns in these datasets. Instead, we argue that a proper factuality evaluation dataset should test a model's ability to reason about current events by retrieving and reading related evidence. To this end, we develop a novel pipeline that leverages natural language feedback from a RAG-based detector to iteratively modify real-time news into deceptive variants that challenge LLMs. Our iterative rewrite decreases the binary classification ROC-AUC by an absolute 17.5 percent for a strong RAG-based GPT-4o detector. Our experiments reveal the important role of RAG in both evaluating and generating challenging news examples, as retrieval-free LLM detectors are vulnerable to unseen events and adversarial attacks, while feedback from RAG-based evaluation helps discover more deceitful patterns.