Verify as You Go: An LLM-Powered Browser Extension for Fake News Detection

TL;DR

Aletheia is introduced, a novel browser extension that leverages Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) to detect fake news and provide evidence-based explanations and its potential as a transparent tool for combating online fake news.

Abstract

The rampant spread of fake news in the digital age poses serious risks to public trust and democratic institutions, underscoring the need for effective, transparent, and user-centered detection tools. Existing browser extensions often fall short due to opaque model behavior, limited explanatory support, and a lack of meaningful user engagement. This paper introduces Aletheia, a novel browser extension that leverages Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) to detect fake news and provide evidence-based explanations. Aletheia further includes two interactive components: a Discussion Hub that enables user dialogue around flagged content and a Stay Informed feature that surfaces recent fact-checks. Through extensive experiments, we show that Aletheia outperforms state-of-the-art baselines in detection performance. Complementing this empirical evaluation, a complementary user study with 250 participants confirms the system's usability and perceived effectiveness, highlighting its potential as a transparent tool for combating online fake news.

Figures (8)

• Figure 1: Aletheia system architecture. The client-side browser extension interfaces with a Flask-based backend server. The backend comprises three primary modules: Fact-Check Fetcher, Community Database, and FakeCheckRAG.
• Figure 2: Snapshots of Aletheia’s user interface: (a) claim submission, (b) system explanation, (c) community discussion, and (d) recent fact-checks.
• Figure 3: The FakeCheckRAG pipeline from claim parsing to classification.
• Figure 4: F1 score across re-search rounds.
• Figure 5: Distribution of user ratings for three core components of Aletheia.