MALicious INTent Dataset and Inoculating LLMs for Enhanced Disinformation Detection

TL;DR

This paper introduces MALINT, a new annotated dataset capturing malicious intent behind disinformation, and proposes intent-based inoculation to improve LLMs' ability to detect disinformation across multiple languages.

Contribution

The work presents MALINT, the first human-annotated corpus for malicious disinformation intent, and develops intent-augmented reasoning to enhance LLMs' detection capabilities.

Findings

Intent-augmented reasoning improves zero-shot disinformation detection.

MALINT dataset supports multi-language disinformation research.

Benchmarking shows LLMs benefit from intent analysis.

Abstract

The intentional creation and spread of disinformation poses a significant threat to public discourse. However, existing English datasets and research rarely address the intentionality behind the disinformation. This work presents MALINT, the first human-annotated English corpus developed in collaboration with expert fact-checkers to capture disinformation and its malicious intent. We utilize our novel corpus to benchmark 12 language models, including small language models (SLMs) such as BERT and large language models (LLMs) like Llama 3.3, on binary and multilabel intent classification tasks. Moreover, inspired by inoculation theory from psychology and communication studies, we investigate whether incorporating knowledge of malicious intent can improve disinformation detection. To this end, we propose intent-based inoculation, an intent-augmented reasoning for LLMs that integrates intent analysis to mitigate the persuasive impact of disinformation. Analysis on six disinformation datasets, five LLMs, and seven languages shows that intent-augmented reasoning improves zero-shot disinformation detection. To support research in intent-aware disinformation detection, we release the MALINT dataset with annotations from each annotation step.