arXiv subjects

Kalina Bontcheva

Publications and source records attributed to Kalina Bontcheva.

At least 19 recordsLinked to original sources

arXiv2026

MigrationNarrate: A Dataset for Detection of Migration Narratives in YouTube Videos

Narratives are central to how social communication is framed, making their detection critical for understanding and analysing public discourse. Prior work has explored narrative detection and extraction across diverse domains; however, migration narratives remain significantly understudied, primarily due to the absence of dedicated annotated datasets. Furthermore, public communication has recently shifted towards video-centric platforms, where narratives are conveyed through multimodal signals and consumed at scale. Despite this shift, narratives in videos remain largely unexplored. To bridge these gaps, we introduce MigrationNarrate, the first multimodal dataset for detection of migration narratives in the UK, consisting of 1,115 YouTube video transcripts annotated using a two-level taxonomy of 12 migration super-narratives and 53 narrative labels. This paper details the dataset design, collection, and annotations; together with benchmark results using a combination of pre-trained encoder models and both open- and closed-source Large Language Models. Finally, a thorough error analysis offers insights for future work.

cs.CV↗

arXiv2026

A Browser-based Open Source Assistant for Multimodal Content Verification

Disinformation and false content produced by generative AI pose a significant challenge for journalists and fact-checkers who must rapidly verify digital media information. While there is an abundance of NLP models for detecting credibility signals such as persuasion techniques, subjectivity, or machine-generated text, such methods often remain inaccessible to non-expert users and are not integrated into their daily workflows as a unified framework. This paper demonstrates the VERIFICATION ASSISTANT, a browser-based tool designed to bridge this gap. The VERIFICATION ASSISTANT, a core component of the widely adopted VERIFICATION PLUGIN (140,000+ users), allows users to submit URLs or media files to a unified interface. It automatically extracts content and routes it to a suite of backend NLP classifiers, delivering actionable credibility signals, estimating AI-generated content, and providing other verification guidance in a clear, easy-to-digest format. This paper showcases the tool architecture, its integration of multiple NLP services, and its real-world application to detecting disinformation.

cs.CL↗

arXiv2026

Truth with a Twist: The Rhetoric of Persuasion in Professional vs. Community-Authored Fact-Checks

This study presents the first large-scale comparison of persuasion techniques present in crowd- versus professionally-written debunks. Using extensive datasets from Community Notes (CNs), EUvsDisinfo, and the Database of Known Fakes (DBKF), we quantify the prevalence and types of persuasion techniques across these fact-checking ecosystems. Contrary to prior hypothesis that community-produced debunks rely more heavily on subjective or persuasive wording, we find no evidence that CNs contain a higher average number of persuasion techniques than professional fact-checks. We additionally identify systematic rhetorical differences between CNs and professional debunking efforts, reflecting differences in institutional norms and topical coverage. Finally, we examine how the crowd evaluates persuasive language in CNs and show that, although notes with more persuasive elements receive slightly higher overall helpfulness ratings, crowd raters are effective at penalising the use of particular problematic rhetorical means

cs.CL↗

arXiv2026

LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems

Automated fact-checking (AFC) systems are susceptible to adversarial attacks, enabling false claims to evade detection. Existing adversarial frameworks typically rely on injecting noise or altering semantics, yet no existing framework exploits the adversarial potential of persuasion techniques against AFC systems, which are widely used in disinformation campaigns to manipulate audiences. In this paper, we introduce a novel class of persuasive adversarial attacks on AFCs by employing an LLM to rephrase claims using persuasion techniques. Considering $15$ techniques grouped into $5$ categories, we study the effects of persuasion on both claim verification and evidence retrieval using a decoupled evaluation strategy. Experiments on the FEVER and FEVEROUS benchmarks show that persuasion attacks can substantially degrade both verification performance and evidence retrieval. Our analysis identifies persuasion techniques as a potent class of adversarial attacks, highlighting the need for more robust AFC systems.

cs.CL↗

arXiv2025

Timeliness, Consensus, and Composition of the Crowd: Community Notes on X

This study presents the first large-scale quantitative analysis of the efficiency of X's Community Notes, a crowdsourced moderation system for identifying and contextualising potentially misleading content. Drawing on over 1.8 million notes, we examine three key dimensions of crowdsourced moderation: participation inequality, consensus formation, and timeliness. Despite the system's goal of collective moderation, we find substantial concentration effect, with the top 10% of contributors producing 58% of all notes (Gini Coefficient = 0.68). The observed consensus is rare-only 11.5% of notes reach agreement on publication, while 69% of posts receive conflicting classifications. A majority of noted posts (approximately 68%) are annotated as "Note Not Needed", reflecting the repurposing of the platform for debate rather than moderation. We found that such posts are paradoxically more likely to yield published notes (OR = 3.12). Temporal analyses show that the notes, on average, are published 65.7 hours after the original post, with longer delays significantly reducing the likelihood of consensus. These results portray Community Notes as a stratified, deliberative system dominated by a small contributor elite, marked by persistent dissensus, and constrained by timeliness. We conclude this study by outlining design strategies to promote equity, faster consensus, and epistemic reliability in community-based moderation.

cs.SI↗

arXiv2025

Tailored untruths: How personalisation challenges LLM safeguards

Large Language Models (LLMs) can generate highly persuasive disinformation, yet little is known about how effectively they personalise it across languages and demographic groups. We present the first large-scale multilingual study of persona-targeted disinformation generation by LLMs. Using a red-teaming methodology, we prompted eight leading models with 324 false narratives and 150 demographic personas in four languages (English, Russian, Portuguese, and Hindi), creating AI-TRAITS, a dataset of 1.6 million personalised disinformation texts. We treat safeguards as compromised whenever a model generates the requested falsehood, whether directly or accompanied by a safety disclaimer. Across models, safeguards failed for 80% of non-personalised prompts and 77.7% of personalised ones, with Grok producing disinformation in over 94% of cases. All models effectively tailored outputs to target personas, employing substantially more persuasive techniques than in non-personalised content. Additional analyses reveal persona-specific linguistic and psychological patterns and show that safeguard effectiveness varies markedly across languages. Together, these findings expose significant weaknesses in current LLM safety mechanisms and highlight the need for more robust, multilingual safeguards against personalised AI-generated disinformation.

cs.CL↗

arXiv2025

A Survey on Automatic Credibility Assessment Using Textual Credibility Signals in the Era of Large Language Models

In the age of social media and generative AI, the ability to automatically assess the credibility of online content has become increasingly critical, complementing traditional approaches to false information detection. Credibility assessment relies on aggregating diverse credibility signals - small units of information, such as content subjectivity, bias, or a presence of persuasion techniques - into a final credibility label/score. However, current research in automatic credibility assessment and credibility signals detection remains highly fragmented, with many signals studied in isolation and lacking integration. Notably, there is a scarcity of approaches that detect and aggregate multiple credibility signals simultaneously. These challenges are further exacerbated by the absence of a comprehensive and up-to-date overview of research works that connects these research efforts under a common framework and identifies shared trends, challenges, and open problems. In this survey, we address this gap by presenting a systematic and comprehensive literature review of 175 research papers, focusing on textual credibility signals within the field of Natural Language Processing (NLP), which undergoes a rapid transformation due to advancements in Large Language Models (LLMs). While positioning the NLP research into the the broader multidisciplinary landscape, we examine both automatic credibility assessment methods as well as the detection of nine categories of credibility signals. We provide an in-depth analysis of three key categories: 1) factuality, subjectivity and bias, 2) persuasion techniques and logical fallacies, and 3) check-worthy and fact-checked claims. In addition to summarising existing methods, datasets, and tools, we outline future research direction and emerging opportunities, with particular attention to evolving challenges posed by generative AI.

cs.CL↗

arXiv2025

GateNLP at SemEval-2025 Task 10: Hierarchical Three-Step Prompting for Multilingual Narrative Classification

The proliferation of online news and the increasing spread of misinformation necessitate robust methods for automatic data analysis. Narrative classification is emerging as a important task, since identifying what is being said online is critical for fact-checkers, policy markers and other professionals working on information studies. This paper presents our approach to SemEval 2025 Task 10 Subtask 2, which aims to classify news articles into a pre-defined two-level taxonomy of main narratives and sub-narratives across multiple languages. We propose Hierarchical Three-Step Prompting (H3Prompt) for multilingual narrative classification. Our methodology follows a three-step Large Language Model (LLM) prompting strategy, where the model first categorises an article into one of two domains (Ukraine-Russia War or Climate Change), then identifies the most relevant main narratives, and finally assigns sub-narratives. Our approach secured the top position on the English test set among 28 competing teams worldwide. The code is available at https://github.com/GateNLP/H3Prompt.

cs.CL↗

arXiv2025

UKElectionNarratives: A Dataset of Misleading Narratives Surrounding Recent UK General Elections

Misleading narratives play a crucial role in shaping public opinion during elections, as they can influence how voters perceive candidates and political parties. This entails the need to detect these narratives accurately. To address this, we introduce the first taxonomy of common misleading narratives that circulated during recent elections in Europe. Based on this taxonomy, we construct and analyse UKElectionNarratives: the first dataset of human-annotated misleading narratives which circulated during the UK General Elections in 2019 and 2024. We also benchmark Pre-trained and Large Language Models (focusing on GPT-4o), studying their effectiveness in detecting election-related misleading narratives. Finally, we discuss potential use cases and make recommendations for future research directions using the proposed codebook and dataset.

cs.CL↗

arXiv2025

A Dataset for Analysing News Framing in Chinese Media

Framing is an essential device in news reporting, allowing the writer to influence public perceptions of current affairs. While there are existing automatic news framing detection datasets in various languages, none of them focus on news framing in the Chinese language which has complex character meanings and unique linguistic features. This study introduces the first Chinese News Framing dataset, to be used as either a stand-alone dataset or a supplementary resource to the SemEval-2023 task 3 dataset. We detail its creation and we run baseline experiments to highlight the need for such a dataset and create benchmarks for future research, providing results obtained through fine-tuning XLM-RoBERTa-Base and using GPT-4o in the zero-shot setting. We find that GPT-4o performs significantly worse than fine-tuned XLM-RoBERTa across all languages. For the Chinese language, we obtain an F1-micro (the performance metric for SemEval task 3, subtask 2) score of 0.719 using only samples from our Chinese News Framing dataset and a score of 0.753 when we augment the SemEval dataset with Chinese news framing samples. With positive news frame detection results, this dataset is a valuable resource for detecting news frames in the Chinese language and is a valuable supplement to the SemEval-2023 task 3 dataset.

cs.CL↗

arXiv2025

A Lightweight Approach for User and Keyword Classification in Controversial Topics

Classifying the stance of individuals on controversial topics and uncovering their concerns is crucial for social scientists and policymakers. Data from Online Social Networks (OSNs), which serve as a proxy to a representative sample of society, offers an opportunity to classify these stances, discover society's concerns regarding controversial topics, and track the evolution of these concerns over time. Consequently, stance classification in OSNs has garnered significant attention from researchers. However, most existing methods for this task often rely on labelled data and utilise the text of users' posts or the interactions between users, necessitating large volumes of data, considerable processing time, and access to information that is not readily available (e.g. users' followers/followees). This paper proposes a lightweight approach for the stance classification of users and keywords in OSNs, aiming at understanding the collective opinion of individuals and their concerns. Our approach employs a tailored random walk model, requiring just one keyword representing each stance, using solely the keywords in social media posts. Experimental results demonstrate the superior performance of our method compared to the baselines, excelling in stance classification of users and keywords, with a running time that, while not the fastest, remains competitive.

cs.SI↗

arXiv2024

A Cross-Domain Study of the Use of Persuasion Techniques in Online Disinformation

Disinformation, irrespective of domain or language, aims to deceive or manipulate public opinion, typically through employing advanced persuasion techniques. Qualitative and quantitative research on the weaponisation of persuasion techniques in disinformation has been mostly topic-specific (e.g., COVID-19) with limited cross-domain studies, resulting in a lack of comprehensive understanding of these strategies. This study employs a state-of-the-art persuasion technique classifier to conduct a large-scale, multi-domain analysis of the role of 16 persuasion techniques in disinformation narratives. It shows how different persuasion techniques are employed disproportionately in different disinformation domains. We also include a detailed case study on climate change disinformation, highlighting how linguistic, psychological, and cultural factors shape the adaptation of persuasion strategies to fit unique thematic contexts.

cs.CY↗

arXiv2024

Lying Blindly: Bypassing ChatGPT's Safeguards to Generate Hard-to-Detect Disinformation Claims

As Large Language Models become more proficient, their misuse in coordinated disinformation campaigns is a growing concern. This study explores the capability of ChatGPT with GPT-3.5 to generate short-form disinformation claims about the war in Ukraine, both in general and on a specific event, which is beyond the GPT-3.5 knowledge cutoff. Unlike prior work, we do not provide the model with human-written disinformation narratives by including them in the prompt. Thus the generated short claims are hallucinations based on prior world knowledge and inference from the minimal prompt. With a straightforward prompting technique, we are able to bypass model safeguards and generate numerous short claims. We compare those against human-authored false claims on the war in Ukraine from ClaimReview, specifically with respect to differences in their linguistic properties. We also evaluate whether AI authorship can be differentiated by human readers or state-of-the-art authorship detection tools. Thus, we demonstrate that ChatGPT can produce realistic, target-specific disinformation claims, even on a specific post-cutoff event, and that they cannot be reliably distinguished by humans or existing automated tools.

cs.CL↗

arXiv2024

Hostility Detection in UK Politics: A Dataset on Online Abuse Targeting MPs

Numerous politicians use social media platforms, particularly X, to engage with their constituents. This interaction allows constituents to pose questions and offer feedback but also exposes politicians to a barrage of hostile responses, especially given the anonymity afforded by social media. They are typically targeted in relation to their governmental role, but the comments also tend to attack their personal identity. This can discredit politicians and reduce public trust in the government. It can also incite anger and disrespect, leading to offline harm and violence. While numerous models exist for detecting hostility in general, they lack the specificity required for political contexts. Furthermore, addressing hostility towards politicians demands tailored approaches due to the distinct language and issues inherent to each country (e.g., Brexit for the UK). To bridge this gap, we construct a dataset of 3,320 English tweets spanning a two-year period manually annotated for hostility towards UK MPs. Our dataset also captures the targeted identity characteristics (race, gender, religion, none) in hostile tweets. We perform linguistic and topical analyses to delve into the unique content of the UK political data. Finally, we evaluate the performance of pre-trained language models and large language models on binary hostility detection and multi-class targeted identity type classification tasks. Our study offers valuable data and insights for future research on the prevalence and nature of politics-related hostility specific to the UK.

cs.CL↗

arXiv2024

Weakly Supervised Veracity Classification with LLM-Predicted Credibility Signals

Credibility signals represent a wide range of heuristics typically used by journalists and fact-checkers to assess the veracity of online content. Automating the extraction of credibility signals presents significant challenges due to the necessity of training high-accuracy, signal-specific extractors, coupled with the lack of sufficiently large annotated datasets. This paper introduces Pastel (Prompted weAk Supervision wiTh crEdibility signaLs), a weakly supervised approach that leverages large language models (LLMs) to extract credibility signals from web content, and subsequently combines them to predict the veracity of content without relying on human supervision. We validate our approach using four article-level misinformation detection datasets, demonstrating that Pastel outperforms zero-shot veracity detection by 38.3% and achieves 86.7% of the performance of the state-of-the-art system trained with human supervision. Moreover, in cross-domain settings where training and testing datasets originate from different domains, Pastel significantly outperforms the state-of-the-art supervised model by 63%. We further study the association between credibility signals and veracity, and perform an ablation study showing the impact of each signal on model performance. Our findings reveal that 12 out of the 19 proposed signals exhibit strong associations with veracity across all datasets, while some signals show domain-specific strengths.

cs.CL↗

arXiv2024

EUvsDisinfo: A Dataset for Multilingual Detection of Pro-Kremlin Disinformation in News Articles

This work introduces EUvsDisinfo, a multilingual dataset of disinformation articles originating from pro-Kremlin outlets, along with trustworthy articles from credible / less biased sources. It is sourced directly from the debunk articles written by experts leading the EUvsDisinfo project. Our dataset is the largest to-date resource in terms of the overall number of articles and distinct languages. It also provides the largest topical and temporal coverage. Using this dataset, we investigate the dissemination of pro-Kremlin disinformation across different languages, uncovering language-specific patterns targeting certain disinformation topics. We further analyse the evolution of topic distribution over an eight-year period, noting a significant surge in disinformation content before the full-scale invasion of Ukraine in 2022. Lastly, we demonstrate the dataset's applicability in training models to effectively distinguish between disinformation and trustworthy content in multilingual settings.

cs.CL↗

arXiv2024

Breaking Language Barriers with MMTweets: Advancing Cross-Lingual Debunked Narrative Retrieval for Fact-Checking

Finding previously debunked narratives involves identifying claims that have already undergone fact-checking. The issue intensifies when similar false claims persist in multiple languages, despite the availability of debunks for several months in another language. Hence, automatically finding debunks (or fact-checks) in multiple languages is crucial to make the best use of scarce fact-checkers' resources. Mainly due to the lack of readily available data, this is an understudied problem, particularly when considering the cross-lingual scenario, i.e. the retrieval of debunks in a language different from the language of the online post being checked. This study introduces cross-lingual debunked narrative retrieval and addresses this research gap by: (i) creating Multilingual Misinformation Tweets (MMTweets): a dataset that stands out, featuring cross-lingual pairs, images, human annotations, and fine-grained labels, making it a comprehensive resource compared to its counterparts; (ii) conducting an extensive experiment to benchmark state-of-the-art cross-lingual retrieval models and introducing multistage retrieval methods tailored for the task; and (iii) comprehensively evaluating retrieval models for their cross-lingual and cross-dataset transfer capabilities within MMTweets, and conducting a retrieval latency analysis. We find that MMTweets presents challenges for cross-lingual debunked narrative retrieval, highlighting areas for improvement in retrieval models. Nonetheless, the study provides valuable insights for creating MMTweets datasets and optimising debunked narrative retrieval models to empower fact-checking endeavours. The dataset and annotation codebook are publicly available at https://doi.org/10.5281/zenodo.10637161.

cs.CL↗

arXiv2024

Addressing Topic Granularity and Hallucination in Large Language Models for Topic Modelling

Large language models (LLMs) with their strong zero-shot topic extraction capabilities offer an alternative to probabilistic topic modelling and closed-set topic classification approaches. As zero-shot topic extractors, LLMs are expected to understand human instructions to generate relevant and non-hallucinated topics based on the given documents. However, LLM-based topic modelling approaches often face difficulties in generating topics with adherence to granularity as specified in human instructions, often resulting in many near-duplicate topics. Furthermore, methods for addressing hallucinated topics generated by LLMs have not yet been investigated. In this paper, we focus on addressing the issues of topic granularity and hallucinations for better LLM-based topic modelling. To this end, we introduce a novel approach that leverages Direct Preference Optimisation (DPO) to fine-tune open-source LLMs, such as Mistral-7B. Our approach does not rely on traditional human annotation to rank preferred answers but employs a reconstruction pipeline to modify raw topics generated by LLMs, thus enabling a fast and efficient training and inference framework. Comparative experiments show that our fine-tuning approach not only significantly improves the LLM's capability to produce more coherent, relevant, and precise topics, but also reduces the number of hallucinated topics.

cs.CL↗