Large Language Models (LLMs) can generate highly persuasive text, raising concerns about their misuse for propaganda, manipulation, and other harmful purposes.This leads us to our central question: Is LLM-generated persuasion more difficult to automatically detect than human-written persuasion?To address this, we categorize controllable generation approaches for producing persuasive content with LLMs and introduce Persuaficial, a high-quality multilingual benchmark covering six languages: English, German, Polish, Italian, French and Russian.Using this benchmark, we conduct extensive empirical evaluations comparing human-authored and LLM-generated persuasive texts.We find that although overtly persuasive LLM-generated texts can be easier to detect than human-written ones, subtle LLMgenerated persuasion consistently degrades automatic detection performance.Beyond detection performance, we provide the first comprehensive linguistic analysis contrasting human and LLM-generated persuasive texts, offering insights that may guide the development of more interpretable and robust detection tools.

Disinformation is an escalating global threat, making it essential to understand its content, dissemination, and evolution. To confront this challenge, researchers have begun grouping related false claims into broader disinformation narratives, which can be tracked across cultures, time periods, and media sources. Analyzing these narratives provides critical insights for developing more effective countermeasures. To this end, we introduce DiNO: Disinformation Narrative Observer, a novel method designed to extract disinformation narratives from news articles. We applied DiNO to news articles on the Ukraine War, COVID-19 and Migration, sourced from disinformation-prone outlets as well as a reputable source. We evaluated the narratives extracted by DiNO by measuring how well their topics and stances aligned with a recognized disinformation narratives dataset. DiNO outperforms competitive narrative mining approaches, including Relatio and CaNarEx, achieving a 41%–44% improvement in topical alignment and a 30%–41% improvment in stance alignment.

Our goal is to support project-based learning in data science education. We scaffold project solutions for four common data science problems: binary classification, multi-class classification, regression and clustering, using template solutions implemented as Jupyter notebooks that can be run on any dataset provided by a student in line with formatting guidelines. For data-specific steps (like feature engineering), we extend our templates using a custom Python library for integrating an LLM with a Jupyter notebook. The library works both for open-source models and paid APIs, and allows a chatbot to be integrated in any cell of a Jupyter notebook. Together, these form an interactive data science AI tutor (DSAIT). We study the interaction patterns of 24 data science students from two universities who attempted to solve a Kaggle challenge using DSAIT's assistance, and conduct a temporal analysis of how these patterns evolved during the task. We provide the templates and Python library used to implement DSAIT to the computer science education community.

Persuasion techniques are powerful rhetorical devices used to sway public opinion in a wide range of media. We present a new corpus of persuasion techniques, focusing on Slavic languages. The corpus contains documents in Bulgarian, Polish, and Russian, annotated with persuasion techniques at the coarse-grained text-span level and fine-grained sentence level. The techniques are drawn from a taxonomy of 25 fine-grained persuasion techniques, grouped under six broad categories of rhetorical persuasion strategies. The corpus contains approximately 7500 text spans from 222 documents that cover topics hotly debated at the national and international levels. We describe the corpus creation process, provide detailed statistics, and examine correlations between topics and persuasion techniques. We use classic ML-based and generative AI-based models to provide baselines and benchmark results for the detection and classification of persuasion techniques at the text-span level and sentence level.

Arkadiusz Modzelewski, Witold Sosnowski, Tiziano Labruna, Adam Wierzbicki, Giovanni Da San Martino. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Disinformation poses a significant threat to democratic societies, public health, and national security.To address this challenge, factchecking experts analyze and track disinformation narratives.However, the process of manually identifying these narratives is highly time-consuming and resource-intensive.In this article, we introduce DiNaM, the first algorithm and structured framework specifically designed for mining disinformation narratives.DiNaM uses a multi-step approach to uncover disinformation narratives.It first leverages Large Language Models (LLMs) to detect false information, then applies clustering techniques to identify underlying disinformation narratives.We evaluated DiNaM's performance using groundtruth disinformation narratives from the EUD-isinfoTest dataset.The evaluation employed the Weighted Chamfer Distance (WCD), which measures the similarity between two sets of embeddings: the ground truth and the predicted disinformation narratives.DiNaM achieved a state-of-the-art WCD score of 0.73, outperforming general-purpose narrative mining methods by a notable margin of 16.4-24.7%.We are releasing DiNaM's codebase and the dataset to the public.

This study presents a novel corpus of 15,356 Polish web articles, including articles identified as containing disinformation.Our dataset enables a multifaceted understanding of disinformation.We present a distinctive multilayered methodology for annotating disinformation in texts.What sets our corpus apart is its focus on uncovering hidden intent and manipulation in disinformative content.A team of experts annotated each article with multiple labels indicating both disinformation creators' intents and the manipulation techniques employed.Additionally, we set new baselines for binary disinformation detection and two multiclass multilabel classification tasks: manipulation techniques and intention types classification.