# ExTax: Explainable Disinformation Detection via Persuasion, Emotion, and Narrative Role Taxonomies

arXiv: https://arxiv.org/abs/2605.27045 · HTML: https://mlsanity.com/paper/2605.27045/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 41 references that are in the map.
- First posted on arXiv 26 May 2026.

## Builds on (most cited first, 14 of 14)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [CoAID: COVID-19 Healthcare Misinformation Dataset](https://mlsanity.com/paper/2006.00885/) (2020)
- [Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4](https://mlsanity.com/paper/2305.14928/) (2023)
- [Crowdsourced Fact-Checking at Twitter: How Does the Crowd Compare With Experts?](https://mlsanity.com/paper/2208.09214/) (2022)
- [Cross-SEAN: A Cross-Stitch Semi-Supervised Neural Attention Model for COVID-19 Fake News Detection](https://mlsanity.com/paper/2102.08924/) (2021)
- [RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning Based on Emotional Information](https://mlsanity.com/paper/2406.11093/) (2024)
- [PCoT: Persuasion-Augmented Chain of Thought for Detecting Fake News and Social Media Disinformation](https://mlsanity.com/paper/2506.06842/) (2025)
- [Industrialized Deception: The Collateral Effects of LLM-Generated Misinformation on Digital Ecosystems](https://mlsanity.com/paper/2601.21963/) (2026)
- [Using Persuasive Writing Strategies to Explain and Detect Health Misinformation](https://mlsanity.com/paper/2211.05985/) (2022)
- [Entity Framing and Role Portrayal in the News](https://mlsanity.com/paper/2502.14718/) (2025)
- [Combining exogenous and endogenous signals with a semi-supervised co-attention network for early detection of COVID-19 fake tweets](https://mlsanity.com/paper/2104.05321/) (2021)
- [Mitigating Biases of Large Language Models in Stance Detection with Counterfactual Augmented Calibration](https://mlsanity.com/paper/2402.14296/) (2024)
- [DRES: Fake news detection by dynamic representation and ensemble selection](https://mlsanity.com/paper/2509.16893/) (2025)

## Abstract (arXiv)

The democratization of LLMs has accelerated the generation and circulation of highly fluent disinformation, making traditional syntax-semantic verification increasingly insufficient. Such deception rarely relies solely on surface-level falsity; instead, it often combines persuasive rhetoric, emotional manipulation, and narrative role construction to influence readers' interpretations through multiple cognitive pathways. However, existing detectors typically emphasize isolated signals -- such as syntax, external knowledge, persuasion, or affective cues -- and therefore struggle to capture the multi-faceted manipulative intents underlying disinformation or provide human-auditable explanations. To address this gap, we present ExTax, a taxonomy-aligned framework for explainable disinformation detection. ExTax unifies persuasive rhetoric, emotional manipulation, and narrative roles into a 17-dimensional taxonomic space, covering 6 persuasive-rhetoric strategies, 5 emotional-manipulation methods, and 6 narrative-role categories. It elicits attributes from multiple frontier LLMs, reconciles their disagreements through Entropy-driven Dynamic Label Smoothing, and fuses the resulting taxonomic representations with contextual encodings via Heterogeneous Multi-Head Attention, grounding each prediction in an interpretable manipulation profile. Across five cross-domain and cross-genre benchmarks, ExTax achieves an overall Macro F1 of 0.8456, outperforming state-of-the-art deep learning and LLM-based baselines. It also remains robust under severe genre imbalance, where the strongest deep baseline degrades from 0.9454 to 0.6194.