23 citations · 93 across the 44 of their papers we have counts for
40 papers · 1 filter
Build it, Break it, Repeat: Benchmarking and improving LLM-manipulated disinformation detection in social media posts
Kevin Thomas, Milosz Kasprzyk, Reuel C Igbokwe Onuigbo +5
Detecting machine-generated disinformation on social media is increasingly difficult as large language models (LLMs) make it easier to generate and rewrite misleading content at sc…
LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems
João A. Leite, Olesya Razuvayevskaya, Kalina Bontcheva +1
Automated fact-checking (AFC) systems are susceptible to adversarial attacks, enabling false claims to evade detection. Existing adversarial frameworks typically rely on injecting…
CACARA: Cross-Modal Alignment Leveraging a Text-Centric Approach for Cost-Effective Multimodal and Multilingual Learning
Diego A. B. Moreira, Alef I. Ferreira, Jhessica Silva +10
As deep learning models evolve, new applications and challenges are rapidly emerging. Tasks that once relied on a single modality, such as text, images, or audio, are now enriched…
Tailored untruths: How personalisation challenges LLM safeguards
João A. Leite, João Luz, Silvia Gargova +5
Large Language Models (LLMs) can generate highly persuasive disinformation, yet little is known about how effectively they personalise it across languages and demographic groups. W…
It's All About In-Context Learning! Teaching Extremely Low-Resource Languages to LLMs
Yue Li, Zhixue Zhao, Carolina Scarton
Extremely low-resource languages, especially those written in rare scripts, as shown in Figure 1, remain largely unsupported by large language models (LLMs). This is due in part to…
GateNLP at SemEval-2025 Task 10: Hierarchical Three-Step Prompting for Multilingual Narrative Classification
Iknoor Singh, Carolina Scarton, Kalina Bontcheva
The proliferation of online news and the increasing spread of misinformation necessitate robust methods for automatic data analysis. Narrative classification is emerging as a impor…
UKElectionNarratives: A Dataset of Misleading Narratives Surrounding Recent UK General Elections
Fatima Haouari, Carolina Scarton, Nicolò Faggiani +5
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 n…
SCRum-9: Multilingual Stance Classification over Rumours on Social Media
Yue Li, Jake Vasilakes, Zhixue Zhao +1
We introduce SCRum-9, the largest multilingual Stance Classification dataset for Rumour analysis in 9 languages, containing 7,516 tweets from X. SCRum-9 goes beyond existing stance…
SemEval-2025 Task 1: AdMIRe -- Advancing Multimodal Idiomaticity Representation
Thomas Pickard, Aline Villavicencio, Maggie Mi +3
Idiomatic expressions present a unique challenge in NLP, as their meanings are often not directly inferable from their constituent words. Despite recent advancements in Large Langu…
Exploring Vision Language Models for Multimodal and Multilingual Stance Detection
Jake Vasilakes, Carolina Scarton, Zhixue Zhao
Social media's global reach amplifies the spread of information, highlighting the need for robust Natural Language Processing tasks like stance detection across languages and modal…
Leveraging Large Language Models for Zero-shot Lay Summarisation in Biomedicine and Beyond
Tomas Goldsack, Carolina Scarton, Chenghua Lin
In this work, we explore the application of Large Language Models to zero-shot Lay Summarisation. We propose a novel two-stage framework for Lay Summarisation based on real-life pr…
Investigating Idiomaticity in Word Representations
Wei He, Tiago Kramer Vieira, Marcos Garcia +3
Idiomatic expressions are an integral part of human languages, often used to express complex ideas in compressed or conventional ways (e.g. eager beaver as a keen and enthusiastic…
A Survey on Automatic Credibility Assessment Using Textual Credibility Signals in the Era of Large Language Models
Ivan Srba, Olesya Razuvayevskaya, João A. Leite +10
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 appr…
Label Set Optimization via Activation Distribution Kurtosis for Zero-shot Classification with Generative Models
Yue Li, Zhixue Zhao, Carolina Scarton
In-context learning (ICL) performance is highly sensitive to prompt design, yet the impact of class label options (e.g. lexicon or order) in zero-shot classification remains undere…
Overview of the BioLaySumm 2024 Shared Task on the Lay Summarization of Biomedical Research Articles
Tomas Goldsack, Carolina Scarton, Matthew Shardlow +1
This paper presents the setup and results of the second edition of the BioLaySumm shared task on the Lay Summarisation of Biomedical Research Articles, hosted at the BioNLP Worksho…
FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data
Haoran Sun, Renren Jin, Shaoyang Xu +10
Large language models (LLMs) have demonstrated prowess in a wide range of tasks. However, many LLMs exhibit significant performance discrepancies between high- and low-resource lan…
Enhancing Idiomatic Representation in Multiple Languages via an Adaptive Contrastive Triplet Loss
Wei He, Marco Idiart, Carolina Scarton +1
Accurately modeling idiomatic or non-compositional language has been a longstanding challenge in Natural Language Processing (NLP). This is partly because these expressions do not…
ATLAS: Improving Lay Summarisation with Attribute-based Control
Zhihao Zhang, Tomas Goldsack, Carolina Scarton +1
Lay summarisation aims to produce summaries of scientific articles that are comprehensible to non-expert audiences. However, previous work assumes a one-size-fits-all approach, whe…
EUvsDisinfo: A Dataset for Multilingual Detection of Pro-Kremlin Disinformation in News Articles
João A. Leite, Olesya Razuvayevskaya, Kalina Bontcheva +1
This work introduces EUvsDisinfo, a multilingual dataset of disinformation articles originating from pro-Kremlin outlets, along with trustworthy articles from credible / less biase…
ExU: AI Models for Examining Multilingual Disinformation Narratives and Understanding their Spread
Jake Vasilakes, Zhixue Zhao, Ivan Vykopal +3
Addressing online disinformation requires analysing narratives across languages to help fact-checkers and journalists sift through large amounts of data. The ExU project focuses on…
Word Boundary Information Isn't Useful for Encoder Language Models
Edward Gow-Smith, Dylan Phelps, Harish Tayyar Madabushi +2
All existing transformer-based approaches to NLP using subword tokenisation algorithms encode whitespace (word boundary information) through the use of special space symbols (such…
Don't Waste a Single Annotation: Improving Single-Label Classifiers Through Soft Labels
Ben Wu, Yue Li, Yida Mu +3
In this paper, we address the limitations of the common data annotation and training methods for objective single-label classification tasks. Typically, when annotating such tasks…
Enhancing Biomedical Lay Summarisation with External Knowledge Graphs
Tomas Goldsack, Zhihao Zhang, Chen Tang +2
Previous approaches for automatic lay summarisation are exclusively reliant on the source article that, given it is written for a technical audience (e.g., researchers), is unlikel…
Analysing State-Backed Propaganda Websites: a New Dataset and Linguistic Study
Freddy Heppell, Kalina Bontcheva, Carolina Scarton
This paper analyses two hitherto unstudied sites sharing state-backed disinformation, Reliable Recent News (rrn.world) and WarOnFakes (waronfakes.com), which publish content in Ara…