PropXplain: Can LLMs Enable Explainable Propaganda Detection?

TL;DR

PropXplain introduces a multilingual dataset and an LLM that jointly detect propaganda and generate explanations, addressing the gap in explainability for propaganda detection across languages.

Contribution

It presents the first explanation-enhanced dataset for propaganda detection in Arabic and English and an LLM capable of both detection and explanation generation.

Findings

Model performs comparably to existing methods.

Generated explanations are of high quality.

Resources will be publicly available.

Abstract

There has been significant research on propagandistic content detection across different modalities and languages. However, most studies have primarily focused on detection, with little attention given to explanations justifying the predicted label. This is largely due to the lack of resources that provide explanations alongside annotated labels. To address this issue, we propose a multilingual (i.e., Arabic and English) explanation-enhanced dataset, the first of its kind. Additionally, we introduce an explanation-enhanced LLM for both label detection and rationale-based explanation generation. Our findings indicate that the model performs comparably while also generating explanations. We will make the dataset and experimental resources publicly available for the research community (https://github.com/firojalam/PropXplain).