Papers by Arkadiusz Modzelewski
DiNO: Disinformation Narrative Observer (2026.acl-long)
Copied to clipboard
| Challenge: | Disinformation is an escalating global threat, making it essential to understand its content, dissemination, and evolution. |
| Approach: | They propose a method to extract disinformation narratives from news articles . they evaluated how well their topics and stances aligned with a recognized disinformation dataset. |
| Outcome: | The proposed method outperforms other narrative mining methods in analyzing disinformation narratives. |
PCoT: Persuasion-Augmented Chain of Thought for Detecting Fake News and Social Media Disinformation (2025.acl-long)
Copied to clipboard
| Challenge: | Psychological studies have shown that infusing persuasion knowledge enhances disinformation detection. |
| Approach: | They introduce a persuasion-augmented chain of thought approach that leverages persulasion to improve disinformation detection in zero-shot classification. |
| Outcome: | The proposed approach outperforms competitive methods by 15% on online news and social media posts. |
EU DisinfoTest: a Benchmark for Evaluating Language Models’ Ability to Detect Disinformation Narratives (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Disinformation narratives can be deceptive and disinformative, designed to sow division, distrust, and fear. |
| Approach: | They propose to evaluate the efficacy of Language Models in identifying disinformation narratives using a Human-in-the-Loop methodology. |
| Outcome: | The EU DisinfoTest evaluates language models on their ability to perform zero-shot classification of disinformation narratives versus credible narratives. |
MIPD: Exploring Manipulation and Intention In a Novel Corpus of Polish Disinformation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Using a unique methodology, we annotated disinformation in Polish with multiple labels indicating both intents and manipulation techniques employed. |
| Approach: | They present a novel corpus of 15,356 Polish web articles annotated with multiple labels indicating both disinformation creators’ intents and manipulation techniques employed. |
| Outcome: | The proposed dataset sheds light on the authors' intention and manipulation techniques in disinformation. |
MALicious INTent Dataset and Inoculating LLMs for Enhanced Disinformation Detection (2026.eacl-long)
Copied to clipboard
Arkadiusz Modzelewski, Witold Sosnowski, Eleni Papadopulos, Elisa Sartori, Tiziano Labruna, Giovanni Da San Martino, Adam Wierzbicki
| Challenge: | Existing studies on intentionality behind disinformation do not address intent behind disinformative agents. |
| Approach: | They propose an intent-augmented reasoning system that integrates intent analysis to mitigate the persuasive impact of disinformation. |
| Outcome: | The proposed corpus is the first human-annotated English corpus to capture disinformation and its malicious intent. |
Detecting Winning Arguments with Large Language Models and Persuasion Strategies (2026.findings-eacl)
Copied to clipboard
| Challenge: | Recent studies have focused on predicting winning arguments, i.e., those that effectively convince a reader to adopt a certain opinion. |
| Approach: | They propose to use large language models with a chain-of-thought framework to guide reasoning over six persuasion strategies to determine persuasiveness. |
| Outcome: | The proposed approach leverages large language models with a chain-of-thought framework that guides reasoning over six persuasion strategies. |
Can AI-Generated Persuasion Be Detected? Persuaficial Benchmark and AI vs. Human Linguistic Differences (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can generate highly persuasive text, raising concerns about misuse for propaganda, manipulation, and other harmful purposes. |
| Approach: | They propose a multilingual benchmark to compare LLM-generated persuasive texts with human-written ones. |
| Outcome: | The proposed benchmark compares human-authored and LLM-generated persuasive texts . it finds that overtly persuasive LLMs are easier to detect than human-written ones . |
DiNaM: Disinformation Narrative Mining with Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Disinformation is a powerful force in digital media, posing serious threats such as physical harm and the erosion of democracy. |
| Approach: | They propose to use a multi-step approach to uncover disinformation narratives by using Large Language Models to detect false information and then using clustering techniques to identify underlying disinformation stories. |
| Outcome: | The proposed algorithm outperforms general-purpose narrative mining methods by 16.4–24.7%. |