Arkaitz Zubiaga

Xia Zeng, Arkaitz Zubiaga

To mitigate the impact of the scarcity of labelled data on fact-checking systems, we focus on few-shot claim verification. Despite recent work on few-shot classification by proposing advanced language models, there is a dearth of research in data annotation prioritisation that improves the selection of the few shots to be labelled for optimal model performance. We propose Active PETs, a novel weighted approach that utilises an ensemble of Pattern Exploiting Training (PET) models based on various language models, to actively select unlabelled data as candidates for annotation. Using Active PETs for few-shot data selection shows consistent improvement over the baseline methods, on two technical fact-checking datasets and using six different pretrained language models. We show further improvement with Active PETs-o, which further integrates an oversampling strategy. Our approach enables effective selection of instances to be labelled where unlabelled data is abundant but resources for labelling are limited, leading to consistently improved few-shot claim verification performance. Our code is available.

Xiaoyu Guo, Jing Ma, Arkaitz Zubiaga

This paper describes the participation of our NUAA-QMUL-AIIT team in the Memotion 3 shared task on meme emotion analysis. We propose a novel multi-modal fusion method, Squeeze-and-Excitation Fusion (SEFusion), and embed it into our system for emotion classification in memes. SEFusion is a simple fusion method that employs fully connected layers, reshaping, and matrix multiplication. SEFusion learns a weight for each modality and then applies it to its own modality feature. We evaluate the performance of our system on the three Memotion 3 sub-tasks. Among all participating systems in this Memotion 3 shared task, our system ranked first on task A, fifth on task B, and second on task C. Our proposed SEFusion provides the flexibility to fuse any features from different modalities. The source code for our method is published on https://github.com/xxxxxxxxy/memotion3-SEFusion.

Xia Zeng, Arkaitz Zubiaga

As part of an automated fact-checking pipeline, the claim veracity classification task consists in determining if a claim is supported by an associated piece of evidence. The complexity of gathering labelled claim-evidence pairs leads to a scarcity of datasets, particularly when dealing with new domains. In this paper, we introduce SEED, a novel vector-based method to few-shot claim veracity classification that aggregates pairwise semantic differences for claim-evidence pairs. We build on the hypothesis that we can simulate class representative vectors that capture average semantic differences for claim-evidence pairs in a class, which can then be used for classification of new instances. We compare the performance of our method with competitive baselines including fine-tuned BERT/RoBERTa models, as well as the state-of-the-art few-shot veracity classification method that leverages language model perplexity. Experiments conducted on the FEVER and SCIFACT datasets show consistent improvements over competitive baselines in few-shot settings. Our code is available.

Peiling Yi, Arkaitz Zubiaga

Cyberbullying is a pervasive problem in online social media, where a bully abuses a victim through a social media session. By investigating cyberbullying perpetrated through social media sessions, recent research has looked into mining patterns and features for modeling and understanding the two defining characteristics of cyberbullying: repetitive behavior and power imbalance. In this survey paper, we define the Session-based Cyberbullying Detection framework that encapsulates the different steps and challenges of the problem. Based on this framework, we provide a comprehensive overview of session-based cyberbullying detection in social media, delving into existing efforts from a data and methodological perspective. Our review leads us to propose evidence-based criteria for a set of best practices to create session-based cyberbullying datasets. In addition, we perform benchmark experiments comparing the performance of state-of-the-art session-based cyberbullying detection models as well as large pre-trained language models across two different datasets. Through our review, we also put forth a set of open challenges as future research directions.

Peiling Yi, Arkaitz Zubiaga

Despite the increasing interest in cyberbullying detection, existing efforts have largely been limited to experiments on a single platform and their generalisability across different social media platforms have received less attention. We propose XP-CB, a novel cross-platform framework based on Transformers and adversarial learning. XP-CB can enhance a Transformer leveraging unlabelled data from the source and target platforms to come up with a common representation while preventing platform-specific training. To validate our proposed framework, we experiment on cyberbullying datasets from three different platforms through six cross-platform configurations, showing its effectiveness with both BERT and RoBERTa as the underlying Transformer models.

Wenjie Yin, Arkaitz Zubiaga

While social media offers freedom of self-expression, abusive language carry significant negative social impact. Driven by the importance of the issue, research in the automated detection of abusive language has witnessed growth and improvement. However, these detection models display a reliance on strongly indicative keywords, such as slurs and profanity. This means that they can falsely (1a) miss abuse without such keywords or (1b) flag non-abuse with such keywords, and that (2) they perform poorly on unseen data. Despite the recognition of these problems, gaps and inconsistencies remain in the literature. In this study, we analyse the impact of keywords from dataset construction to model behaviour in detail, with a focus on how models make mistakes on (1a) and (1b), and how (1a) and (1b) interact with (2). Through the analysis, we provide suggestions for future research to address all three problems.

Rabab Alkhalifa, Elena Kochkina, Arkaitz Zubiaga

Performance of text classification models tends to drop over time due to changes in data, which limits the lifetime of a pretrained model. Therefore an ability to predict a model's ability to persist over time can help design models that can be effectively used over a longer period of time. In this paper, we provide a thorough discussion into the problem, establish an evaluation setup for the task. We look at this problem from a practical perspective by assessing the ability of a wide range of language models and classification algorithms to persist over time, as well as how dataset characteristics can help predict the temporal stability of different models. We perform longitudinal classification experiments on three datasets spanning between 6 and 19 years, and involving diverse tasks and types of data. By splitting the longitudinal datasets into years, we perform a comprehensive set of experiments by training and testing across data that are different numbers of years apart from each other, both in the past and in the future. This enables a gradual investigation into the impact of the temporal gap between training and test sets on the classification performance, as well as measuring the extent of the persistence over time.

Wenjie Yin, Vibhor Agarwal, Aiqi Jiang et al.

Supervised approaches generally rely on majority-based labels. However, it is hard to achieve high agreement among annotators in subjective tasks such as hate speech detection. Existing neural network models principally regard labels as categorical variables, while ignoring the semantic information in diverse label texts. In this paper, we propose AnnoBERT, a first-of-its-kind architecture integrating annotator characteristics and label text with a transformer-based model to detect hate speech, with unique representations based on each annotator's characteristics via Collaborative Topic Regression (CTR) and integrate label text to enrich textual representations. During training, the model associates annotators with their label choices given a piece of text; during evaluation, when label information is not available, the model predicts the aggregated label given by the participating annotators by utilising the learnt association. The proposed approach displayed an advantage in detecting hate speech, especially in the minority class and edge cases with annotator disagreement. Improvement in the overall performance is the largest when the dataset is more label-imbalanced, suggesting its practical value in identifying real-world hate speech, as the volume of hate speech in-the-wild is extremely small on social media, when compared with normal (non-hate) speech. Through ablation studies, we show the relative contributions of annotator embeddings and label text to the model performance, and tested a range of alternative annotator embeddings and label text combinations.

Parisa Jamadi Khiabani, Arkaitz Zubiaga

Despite the increasing popularity of the stance detection task, existing approaches are predominantly limited to using the textual content of social media posts for the classification, overlooking the social nature of the task. The stance detection task becomes particularly challenging in cross-target classification scenarios, where even in few-shot training settings the model needs to predict the stance towards new targets for which the model has only seen few relevant samples during training. To address the cross-target stance detection in social media by leveraging the social nature of the task, we introduce CT-TN, a novel model that aggregates multimodal embeddings derived from both textual and network features of the data. We conduct experiments in a few-shot cross-target scenario on six different combinations of source-destination target pairs. By comparing CT-TN with state-of-the-art cross-target stance detection models, we demonstrate the effectiveness of our model by achieving average performance improvements ranging from 11% to 21% across different baseline models. Experiments with different numbers of shots show that CT-TN can outperform other models after seeing 300 instances of the destination target. Further, ablation experiments demonstrate the positive contribution of each of the components of CT-TN towards the final performance. We further analyse the network interactions between social media users, which reveal the potential of using social features for cross-target stance detection.

M. Arana-Catania, Elena Kochkina, Arkaitz Zubiaga et al.

We present a comprehensive work on automated veracity assessment from dataset creation to developing novel methods based on Natural Language Inference (NLI), focusing on misinformation related to the COVID-19 pandemic. We first describe the construction of the novel PANACEA dataset consisting of heterogeneous claims on COVID-19 and their respective information sources. The dataset construction includes work on retrieval techniques and similarity measurements to ensure a unique set of claims. We then propose novel techniques for automated veracity assessment based on Natural Language Inference including graph convolutional networks and attention based approaches. We have carried out experiments on evidence retrieval and veracity assessment on the dataset using the proposed techniques and found them competitive with SOTA methods, and provided a detailed discussion.

Runcong Zhao, Miguel Arana-Catania, Lixing Zhu et al.

In this demo, we introduce a web-based misinformation detection system PANACEA on COVID-19 related claims, which has two modules, fact-checking and rumour detection. Our fact-checking module, which is supported by novel natural language inference methods with a self-attention network, outperforms state-of-the-art approaches. It is also able to give automated veracity assessment and ranked supporting evidence with the stance towards the claim to be checked. In addition, PANACEA adapts the bi-directional graph convolutional networks model, which is able to detect rumours based on comment networks of related tweets, instead of relying on the knowledge base. This rumour detection module assists by warning the users in the early stages when a knowledge base may not be available.

Parisa Jamadi Khiabani, Arkaitz Zubiaga

Stance detection is the task of determining the viewpoint expressed in a text towards a given target. A specific direction within the task focuses on cross-target stance detection, where a model trained on samples pertaining to certain targets is then applied to a new, unseen target. With the increasing need to analyze and mining viewpoints and opinions online, the task has recently seen a significant surge in interest. This review paper examines the advancements in cross-target stance detection over the last decade, highlighting the evolution from basic statistical methods to contemporary neural and LLM-based models. These advancements have led to notable improvements in accuracy and adaptability. Innovative approaches include the use of topic-grouped attention and adversarial learning for zero-shot detection, as well as fine-tuning techniques that enhance model robustness. Additionally, prompt-tuning methods and the integration of external knowledge have further refined model performance. A comprehensive overview of the datasets used for evaluating these models is also provided, offering valuable insights into the progress and challenges in the field. We conclude by highlighting emerging directions of research and by suggesting avenues for future work in the task.

Amani S. Abumansour, Arkaitz Zubiaga

An important component of an automated fact-checking system is the claim check-worthiness detection system, which ranks sentences by prioritising them based on their need to be checked. Despite a body of research tackling the task, previous research has overlooked the challenging nature of identifying check-worthy claims across different topics. In this paper, we assess and quantify the challenge of detecting check-worthy claims for new, unseen topics. After highlighting the problem, we propose the AraCWA model to mitigate the performance deterioration when detecting check-worthy claims across topics. The AraCWA model enables boosting the performance for new topics by incorporating two components for few-shot learning and data augmentation. Using a publicly available dataset of Arabic tweets consisting of 14 different topics, we demonstrate that our proposed data augmentation strategy achieves substantial improvements across topics overall, where the extent of the improvement varies across topics. Further, we analyse the semantic similarities between topics, suggesting that the similarity metric could be used as a proxy to determine the difficulty level of an unseen topic prior to undertaking the task of labelling the underlying sentences.

Weihe Zhai, Arkaitz Zubiaga

The fusion of language models (LMs) and knowledge graphs (KGs) is widely used in commonsense question answering, but generating faithful explanations remains challenging. Current methods often overlook path decoding faithfulness, leading to divergence between graph encoder outputs and model predictions. We identify confounding effects and LM-KG misalignment as key factors causing spurious explanations. To address this, we introduce the LM-KG Fidelity metric to assess KG representation reliability and propose the LM-KG Distribution-aware Alignment (\textit{LKDA}) algorithm to improve explanation faithfulness. Without ground truth, we evaluate KG explanations using the proposed Fidelity-Sparsity Trade-off Curve. Experiments on CommonsenseQA and OpenBookQA show that LKDA significantly enhances explanation fidelity and model performance, highlighting the need to address distributional misalignment for reliable commonsense reasoning.

Aiqi Jiang, Arkaitz Zubiaga

The goal of sexism detection is to mitigate negative online content targeting certain gender groups of people. However, the limited availability of labeled sexism-related datasets makes it problematic to identify online sexism for low-resource languages. In this paper, we address the task of automatic sexism detection in social media for one low-resource language -- Chinese. Rather than collecting new sexism data or building cross-lingual transfer learning models, we develop a cross-lingual domain-aware semantic specialisation system in order to make the most of existing data. Semantic specialisation is a technique for retrofitting pre-trained distributional word vectors by integrating external linguistic knowledge (such as lexico-semantic relations) into the specialised feature space. To do this, we leverage semantic resources for sexism from a high-resource language (English) to specialise pre-trained word vectors in the target language (Chinese) to inject domain knowledge. We demonstrate the benefit of our sexist word embeddings (SexWEs) specialised by our framework via intrinsic evaluation of word similarity and extrinsic evaluation of sexism detection. Compared with other specialisation approaches and Chinese baseline word vectors, our SexWEs shows an average score improvement of 0.033 and 0.064 in both intrinsic and extrinsic evaluations, respectively. The ablative results and visualisation of SexWEs also prove the effectiveness of our framework on retrofitting word vectors in low-resource languages.

Hyunkyung Park, Arkaitz Zubiaga

Automated fact-checking in dialogue involves multi-turn conversations where colloquial language is frequent yet understudied. To address this gap, we propose a conservative rewrite candidate for each response claim via staged de-colloquialisation, combining lightweight surface normalisation with scoped in-claim coreference resolution. We then introduce BiCon-Gate, a semantics-aware consistency gate that selects the rewrite candidate only when it is semantically supported by the dialogue context, otherwise falling back to the original claim. This gated selection stabilises downstream fact-checking and yields gains in both evidence retrieval and fact verification. On the DialFact benchmark, our approach improves retrieval and verification, with particularly strong gains on SUPPORTS, and outperforms competitive baselines, including a decoder-based one-shot LLM rewrite that attempts to perform all de-colloquialisation steps in a single pass.

Xiaoyu Guo, Jing Ma, Arkaitz Zubiaga

Memes have gained popularity as a means to share visual ideas through the Internet and social media by mixing text, images and videos, often for humorous purposes. Research enabling automated analysis of memes has gained attention in recent years, including among others the task of classifying the emotion expressed in memes. In this paper, we propose a novel model, cluster-based deep ensemble learning (CDEL), for emotion classification in memes. CDEL is a hybrid model that leverages the benefits of a deep learning model in combination with a clustering algorithm, which enhances the model with additional information after clustering memes with similar facial features. We evaluate the performance of CDEL on a benchmark dataset for emotion classification, proving its effectiveness by outperforming a wide range of baseline models and achieving state-of-the-art performance. Further evaluation through ablated models demonstrates the effectiveness of the different components of CDEL.

Rrubaa Panchendrarajan, Arkaitz Zubiaga

Recurrent claims present a major challenge for automated fact-checking systems designed to combat misinformation, especially in multilingual settings. While tasks such as claim matching and fact-checked claim retrieval aim to address this problem by linking claim pairs, the broader challenge of effectively representing groups of similar claims that can be resolved with the same fact-check via claim clustering remains relatively underexplored. To address this gap, we introduce Claim2Vec, the first multilingual embedding model optimized to represent fact-check claims as vectors in an improved semantic embedding space. We fine-tune a multilingual encoder using contrastive learning with similar multilingual claim pairs. Experiments on the claim clustering task using three datasets, 14 multilingual embedding models, and 7 clustering algorithms demonstrate that Claim2Vec significantly improves clustering performance. Specifically, it enhances both cluster label alignment and the geometric structure of the embedding space across different cluster configurations. Our multilingual analysis shows that clusters containing multiple languages benefit from fine-tuning, demonstrating cross-lingual knowledge transfer.

Rafael Martins Frade, Rrubaa Panchendrarajan, Arkaitz Zubiaga

Online disinformation poses an escalating threat to society, driven increasingly by the rapid spread of misleading content across both multimedia and multilingual platforms. While automated fact-checking methods have advanced in recent years, their effectiveness remains constrained by the scarcity of datasets that reflect these real-world complexities. To address this gap, we first present MultiCaption, a new dataset specifically designed for detecting contradictions in visual claims. Pairs of claims referring to the same image or video were labeled through multiple strategies to determine whether they contradict each other. The resulting dataset comprises 11,088 visual claims in 64 languages, offering a unique resource for building and evaluating misinformation-detection systems in truly multimodal and multilingual environments. We then provide comprehensive experiments using transformer-based architectures, natural language inference models, and large language models, establishing strong baselines for future research. The results show that MultiCaption is more challenging than standard NLI tasks, requiring task-specific finetuning for strong performance. Moreover, the gains from multilingual training and testing highlight the dataset's potential for building effective multilingual fact-checking pipelines without relying on machine translation.

Xia Zeng, Arkaitz Zubiaga

Claim verification is an essential step in the automated fact-checking pipeline which assesses the veracity of a claim against a piece of evidence. In this work, we explore the potential of few-shot claim verification, where only very limited data is available for supervision. We propose MAPLE (Micro Analysis of Pairwise Language Evolution), a pioneering approach that explores the alignment between a claim and its evidence with a small seq2seq model and a novel semantic measure. Its innovative utilization of micro language evolution path leverages unlabelled pairwise data to facilitate claim verification while imposing low demand on data annotations and computing resources. MAPLE demonstrates significant performance improvements over SOTA baselines SEED, PET and LLaMA 2 across three fact-checking datasets: FEVER, Climate FEVER, and SciFact. Data and code are available here: https://github.com/XiaZeng0223/MAPLE

Yufeng Li, Rrubaa Panchendrarajan, Arkaitz Zubiaga

The rapid dissemination of information through social media and the Internet has posed a significant challenge for fact-checking, among others in identifying check-worthy claims that fact-checkers should pay attention to, i.e. filtering claims needing fact-checking from a large pool of sentences. This challenge has stressed the need to focus on determining the priority of claims, specifically which claims are worth to be fact-checked. Despite advancements in this area in recent years, the application of large language models (LLMs), such as GPT, has only recently drawn attention in studies. However, many open-source LLMs remain underexplored. Therefore, this study investigates the application of eight prominent open-source LLMs with fine-tuning and prompt engineering to identify check-worthy statements from political transcriptions. Further, we propose a two-step data pruning approach to automatically identify high-quality training data instances for effective learning. The efficiency of our approach is demonstrated through evaluations on the English language dataset as part of the check-worthiness estimation task of CheckThat! 2024. Further, the experiments conducted with data pruning demonstrate that competitive performance can be achieved with only about 44\% of the training data. Our team ranked first in the check-worthiness estimation task in the English language.

Rrubaa Panchendrarajan, Arkaitz Zubiaga

Automated fact-checking has drawn considerable attention over the past few decades due to the increase in the diffusion of misinformation on online platforms. This is often carried out as a sequence of tasks comprising (i) the detection of sentences circulating in online platforms which constitute claims needing verification, followed by (ii) the verification process of those claims. This survey focuses on the former, by discussing existing efforts towards detecting claims needing fact-checking, with a particular focus on multilingual data and methods. This is a challenging and fertile direction where existing methods are yet far from matching human performance due to the profoundly challenging nature of the issue. Especially, the dissemination of information across multiple social platforms, articulated in multiple languages and modalities demands more generalized solutions for combating misinformation. Focusing on multilingual misinformation, we present a comprehensive survey of existing multilingual claim detection research. We present state-of-the-art multilingual claim detection research categorized into three key factors of the problem, verifiability, priority, and similarity. Further, we present a detailed overview of the existing multilingual datasets along with the challenges and suggest possible future advancements.

Rrubaa Panchendrarajan, Arkaitz Zubiaga

The advancement of machine learning and symbolic approaches have underscored their strengths and weaknesses in Natural Language Processing (NLP). While machine learning approaches are powerful in identifying patterns in data, they often fall short in learning commonsense and the factual knowledge required for the NLP tasks. Meanwhile, the symbolic methods excel in representing knowledge-rich data. However, they struggle to adapt dynamic data and generalize the knowledge. Bridging these two paradigms through hybrid approaches enables the alleviation of weaknesses in both while preserving their strengths. Recent studies extol the virtues of this union, showcasing promising results in a wide range of NLP tasks. In this paper, we present an overview of hybrid approaches used for NLP. Specifically, we delve into the state-of-the-art hybrid approaches used for a broad spectrum of NLP tasks requiring natural language understanding, generation, and reasoning. Furthermore, we discuss the existing resources available for hybrid approaches for NLP along with the challenges and future directions, offering a roadmap for future research avenues.

Hiu Ting Lau, Arkaitz Zubiaga

Natural Language Generation has been rapidly developing with the advent of large language models (LLMs). While their usage has sparked significant attention from the general public, it is important for readers to be aware when a piece of text is LLM-generated. This has brought about the need for building models that enable automated LLM-generated text detection, with the aim of mitigating potential negative outcomes of such content. Existing LLM-generated detectors show competitive performances in telling apart LLM-generated and human-written text, but this performance is likely to deteriorate when paraphrased texts are considered. In this study, we devise a new data collection strategy to collect Human & LLM Paraphrase Collection (HLPC), a first-of-its-kind dataset that incorporates human-written texts and paraphrases, as well as LLM-generated texts and paraphrases. With the aim of understanding the effects of human-written paraphrases on the performance of state-of-the-art LLM-generated text detectors OpenAI RoBERTa and watermark detectors, we perform classification experiments that incorporate human-written paraphrases, watermarked and non-watermarked LLM-generated documents from GPT and OPT, and LLM-generated paraphrases from DIPPER and BART. The results show that the inclusion of human-written paraphrases has a significant impact of LLM-generated detector performance, promoting TPR@1%FPR with a possible trade-off of AUROC and accuracy.

Dina Pisarevskaya, Arkaitz Zubiaga

The claim matching (CM) task can benefit an automated fact-checking pipeline by putting together claims that can be resolved with the same fact-check. In this work, we are the first to explore zero-shot and few-shot learning approaches to the task. We consider CM as a binary classification task and experiment with a set of instruction-following large language models (GPT-3.5-turbo, Gemini-1.5-flash, Mistral-7B-Instruct, and Llama-3-8B-Instruct), investigating prompt templates. We introduce a new CM dataset, ClaimMatch, which will be released upon acceptance. We put LLMs to the test in the CM task and find that it can be tackled by leveraging more mature yet similar tasks such as natural language inference or paraphrase detection. We also propose a pipeline for CM, which we evaluate on texts of different lengths.

Aiqi Jiang, Arkaitz Zubiaga

The growing prevalence and rapid evolution of offensive language in social media amplify the complexities of detection, particularly highlighting the challenges in identifying such content across diverse languages. This survey presents a systematic and comprehensive exploration of Cross-Lingual Transfer Learning (CLTL) techniques in offensive language detection in social media. Our study stands as the first holistic overview to focus exclusively on the cross-lingual scenario in this domain. We analyse 67 relevant papers and categorise these studies across various dimensions, including the characteristics of multilingual datasets used, the cross-lingual resources employed, and the specific CLTL strategies implemented. According to "what to transfer", we also summarise three main CLTL transfer approaches: instance, feature, and parameter transfer. Additionally, we shed light on the current challenges and future research opportunities in this field. Furthermore, we have made our survey resources available online, including two comprehensive tables that provide accessible references to the multilingual datasets and CLTL methods used in the reviewed literature.

Antonia Karamolegkou, Angana Borah, Eunjung Cho et al.

Recent advancements in large language models (LLMs) have unlocked unprecedented possibilities across a range of applications. However, as a community, we believe that the field of Natural Language Processing (NLP) has a growing need to approach deployment with greater intentionality and responsibility. In alignment with the broader vision of AI for Social Good (Tomašev et al., 2020), this paper examines the role of NLP in addressing pressing societal challenges. Through a cross-disciplinary analysis of social goals and emerging risks, we highlight promising research directions and outline challenges that must be addressed to ensure responsible and equitable progress in NLP4SG research.

Rrubaa Panchendrarajan, Arkaitz Zubiaga

Identifying claims requiring verification is a critical task in automated fact-checking, especially given the proliferation of misinformation on social media platforms. Despite notable progress, challenges remain-particularly in handling multilingual data prevalent in online discourse. Recent efforts have focused on fine-tuning pre-trained multilingual language models to address this. While these models can handle multiple languages, their ability to effectively transfer cross-lingual knowledge for detecting claims spreading on social media remains under-explored. In this paper, we introduce EX-Claim, an entity-aware cross-lingual claim detection model that generalizes well to handle multilingual claims. The model leverages entity information derived from named entity recognition and entity linking techniques to improve the language-level performance of both seen and unseen languages during training. Extensive experiments conducted on three datasets from different social media platforms demonstrate that our proposed model stands out as an effective solution, demonstrating consistent performance gains across 27 languages and robust knowledge transfer between languages seen and unseen during training.

Aida Halitaj, Arkaitz Zubiaga

Citation Worthiness Detection (CWD) consists in determining which sentences, within an article or collection, should be backed up with a citation to validate the information it provides. This study, introduces ALPET, a framework combining Active Learning (AL) and Pattern-Exploiting Training (PET), to enhance CWD for languages with limited data resources. Applied to Catalan, Basque, and Albanian Wikipedia datasets, ALPET outperforms the existing CCW baseline while reducing the amount of labeled data in some cases above 80\%. ALPET's performance plateaus after 300 labeled samples, showing it suitability for low-resource scenarios where large, labeled datasets are not common. While specific active learning query strategies, like those employing K-Means clustering, can offer advantages, their effectiveness is not universal and often yields marginal gains over random sampling, particularly with smaller datasets. This suggests that random sampling, despite its simplicity, remains a strong baseline for CWD in constraint resource environments. Overall, ALPET's ability to achieve high performance with fewer labeled samples makes it a promising tool for enhancing the verifiability of online content in low-resource language settings.

Peiling Yi, Arkaitz Zubiaga, Yunfei Long

Existing research on detecting cyberbullying incidents on social media has primarily concentrated on harassment and is typically approached as a binary classification task. However, cyberbullying encompasses various forms, such as denigration and harassment, which celebrities frequently face. Furthermore, suitable training data for these diverse forms of cyberbullying remains scarce. In this study, we first develop a celebrity cyberbullying dataset that encompasses two distinct types of incidents: harassment and defamation. We investigate various types of transformer-based models, namely masked (RoBERTa, Bert and DistilBert), replacing(Electra), autoregressive (XLnet), masked&permuted (Mpnet), text-text (T5) and large language models (Llama2 and Llama3) under low source settings. We find that they perform competitively on explicit harassment binary detection. However, their performance is substantially lower on harassment and denigration multi-classification tasks. Therefore, we propose an emotion-adaptive training framework (EAT) that helps transfer knowledge from the domain of emotion detection to the domain of cyberbullying detection to help detect indirect cyberbullying events. EAT consistently improves the average macro F1, precision and recall by 20% in cyberbullying detection tasks across nine transformer-based models under low-resource settings. Our claims are supported by intuitive theoretical insights and extensive experiments.

Parisa Jamadi Khiabani, Arkaitz Zubiaga

Stance detection, as the task of determining the viewpoint of a social media post towards a target as 'favor' or 'against', has been understudied in the challenging yet realistic scenario where there is limited labeled data for a certain target. Our work advances research in few-shot stance detection by introducing SocialPET, a socially informed approach to leveraging language models for the task. Our proposed approach builds on the Pattern Exploiting Training (PET) technique, which addresses classification tasks as cloze questions through the use of language models. To enhance the approach with social awareness, we exploit the social network structure surrounding social media posts. We prove the effectiveness of SocialPET on two stance datasets, Multi-target and P-Stance, outperforming competitive stance detection models as well as the base model, PET, where the labeled instances for the target under study is as few as 100. When we delve into the results, we observe that SocialPET is comparatively strong in identifying instances of the `against' class, where baseline models underperform.

Rrubaa Panchendrarajan, Rubén Míguez, Arkaitz Zubiaga

In the context of fact-checking, claims are often repeated across various platforms and in different languages, which can benefit from a process that reduces this redundancy. While retrieving previously fact-checked claims has been investigated as a solution, the growing number of unverified claims and expanding size of fact-checked databases calls for alternative, more efficient solutions. A promising solution is to group claims that discuss the same underlying facts into clusters to improve claim retrieval and validation. However, research on claim clustering is hindered by the lack of suitable datasets. To bridge this gap, we introduce \textit{MultiClaimNet}, a collection of three multilingual claim cluster datasets containing claims in 86 languages across diverse topics. Claim clusters are formed automatically from claim-matching pairs with limited manual intervention. We leverage two existing claim-matching datasets to form the smaller datasets within \textit{MultiClaimNet}. To build the larger dataset, we propose and validate an approach involving retrieval of approximate nearest neighbors to form candidate claim pairs and an automated annotation of claim similarity using large language models. This larger dataset contains 85.3K fact-checked claims written in 78 languages. We further conduct extensive experiments using various clustering techniques and sentence embedding models to establish baseline performance. Our datasets and findings provide a strong foundation for scalable claim clustering, contributing to efficient fact-checking pipelines.

Xiangyan Chen, Yufeng Li, Yujian Gan et al.

Large Language Models (LLMs) are known to produce hallucinations - factually incorrect or fabricated information - which poses significant challenges for many Natural Language Processing (NLP) applications, such as dialogue systems. As a result, detecting hallucinations has become a critical area of research. Current approaches to hallucination detection in dialogue systems primarily focus on verifying the factual consistency of generated responses. However, these responses often contain a mix of accurate, inaccurate or unverifiable facts, making one factual label overly simplistic and coarse-grained. In this paper, we introduce a benchmark, FineDialFact, for fine-grained dialogue fact verification, which involves verifying atomic facts extracted from dialogue responses. To support this, we construct a dataset based on publicly available dialogue datasets and evaluate it using various baseline methods. Experimental results demonstrate that methods incorporating Chain-of-Thought (CoT) reasoning can enhance performance in dialogue fact verification. Despite this, the best F1-score achieved on the HybriDialogue, an open-domain dialogue dataset, is only 0.75, indicating that the benchmark remains a challenging task for future research. Our dataset and code will be public on GitHub.

Beining Xu, Arkaitz Zubiaga

Large Language Models (LLMs) have demonstrated exceptional performance on a range of downstream NLP tasks by generating text that closely resembles human writing. However, the ease of achieving this similarity raises concerns from potential malicious uses at scale by bad actors, as LLM-generated text becomes increasingly difficult to discern from human text. Although detection methods have been developed to address this issue, bad actors can further manipulate LLM-generated texts to make them less detectable. In this work, we study how further editing texts with Reinforcement Learning from Human Feedback (RLHF), which aligns model outputs with human preferences, affects (a) the quality of generated texts for two tasks, and (b) the performance of LLM-generated text detectors, looking at both training-based and zero-shot detection methods. Although RLHF improves the quality of LLM-generated texts, we find that it also tends to produce more detectable, lengthy, and repetitive outputs. Additionally, we observe that training-based detectors are vulnerable to short texts and to texts that incorporate code, whereas zero-shot detectors exhibit greater robustness.

Raneem Alharthi, Rajwa Alharthi, Ravi Shekhar et al.

Despite the growing body of research tackling offensive language in social media, this research is predominantly reactive, determining if content already posted in social media is abusive. There is a gap in predictive approaches, which we address in our study by enabling to predict the volume of abusive replies a tweet will receive after being posted. We formulate the problem from the perspective of a social media user asking: ``if I post a certain message on social media, is it possible to predict the volume of abusive replies it might receive?'' We look at four types of features, namely text, text metadata, tweet metadata, and account features, which also help us understand the extent to which the user or the content helps predict the number of abusive replies. This, in turn, helps us develop a model to support social media users in finding the best way to post content. One of our objectives is also to determine the extent to which the volume of abusive replies that a tweet will get are motivated by the content of the tweet or by the identity of the user posting it. Our study finds that one can build a model that performs competitively by developing a comprehensive set of features derived from the content of the message that is going to be posted. In addition, our study suggests that features derived from the user's identity do not impact model performance, hence suggesting that it is especially the content of a post that triggers abusive replies rather than who the user is.

Yufeng Li, Rrubaa Panchendrarajan, Arkaitz Zubiaga

Verifiable claim detection asks whether a claim expresses a factual statement that can, in principle, be assessed against external evidence. As an early filtering stage in automated fact-checking, it plays an important role in reducing the burden on downstream verification components. However, existing approaches to claim detection, whether based on check-worthiness or verifiability, rely solely on the claim text itself. This is a notable limitation for verifiable claim detection in particular, where determining whether a claim is checkable may benefit from knowing what entities and events it refers to and whether relevant information exists to support verification. Inspired by the established role of evidence retrieval in later-stage claim verification, we propose Context-Driven Claim Detection (ContextClaim), a paradigm that advances retrieval to the detection stage. ContextClaim extracts entity mentions from the input claim, retrieves relevant information from Wikipedia as a structured knowledge source, and employs large language models to produce concise contextual summaries for downstream classification. We evaluate ContextClaim on two datasets covering different topics and text genres, the CheckThat! 2022 COVID-19 Twitter dataset and the PoliClaim political debate dataset, across encoder-only and decoder-only models under fine-tuning, zero-shot, and few-shot settings. Results show that context augmentation can improve verifiable claim detection, although its effectiveness varies across domains, model architectures, and learning settings. Through component analysis, human evaluation, and error analysis, we further examine when and why the retrieved context contributes to more reliable verifiability judgments.

Dina Pisarevskaya, Arkaitz Zubiaga

We present a novel agent-based approach for the automated claim matching task with instruction-following LLMs. We propose a two-step pipeline that first generates prompts with LLMs, to then perform claim matching as a binary classification task with LLMs. We demonstrate that LLM-generated prompts can outperform SOTA with human-generated prompts, and that smaller LLMs can do as well as larger ones in the generation process, allowing to save computational resources. We also demonstrate the effectiveness of using different LLMs for each step of the pipeline, i.e. using an LLM for prompt generation, and another for claim matching. Our investigation into the prompt generation process in turn reveals insights into the LLMs' understanding of claim matching.

Abdulhady Abas Abdullah, Arkaitz Zubiaga, Seyedali Mirjalili et al.

This review surveys the rapid evolution of Meta AI's LLaMA (Large Language Model Meta AI) series - from LLaMA 1 through LLaMA 4 and the specialized parameter-efficient fine-tuning (PEFT) methods developed for these models. We first describe the LLaMA family of foundation models (7B-65B to 288B parameters), their architectures (including native multimodal and Mixtureof-Experts variants), and key performance characteristics. We then describe and discuss the concept of PEFT, which adapts large pre-trained models by updating only a small subset of parameters, and review five PEFT methods that have been applied to LLaMA: LoRA (Low-Rank Adaptation), LLaMA-Adapter V1 and V2, LLaMA-Excitor, and QLoRA (Quantized LoRA). We discuss each method's mechanism, parameter savings, and example application to LLaMA (e.g., instruction tuning, multimodal tasks). We provide structured discussion and analysis of model and adapter architectures, parameter counts, and benchmark results (including examples where fine-tuned LLaMA models outperform larger baselines). Finally, we examine real-world use cases where LLaMA-based models and PEFT have been successfully applied (e.g., legal and medical domains), and we discuss ongoing challenges and future research directions (such as scaling to even larger contexts and improving robustness). This survey paper provides a one-stop resource for ML researchers and practitioners interested in LLaMA models and efficient fine-tuning strategies.

Ali Khairallah, Arkaitz Zubiaga

We introduce ALHD, the first large-scale comprehensive Arabic dataset explicitly designed to distinguish between human- and LLM-generated texts. ALHD spans three genres (news, social media, reviews), covering both MSA and dialectal Arabic, and contains over 400K balanced samples generated by three leading LLMs and originated from multiple human sources, which enables studying generalizability in Arabic LLM-genearted text detection. We provide rigorous preprocessing, rich annotations, and standardized balanced splits to support reproducibility. In addition, we present, analyze and discuss benchmark experiments using our new dataset, in turn identifying gaps and proposing future research directions. Benchmarking across traditional classifiers, BERT-based models, and LLMs (zero-shot and few-shot) demonstrates that fine-tuned BERT models achieve competitive performance, outperforming LLM-based models. Results are however not always consistent, as we observe challenges when generalizing across genres; indeed, models struggle to generalize when they need to deal with unseen patterns in cross-genre settings, and these challenges are particularly prominent when dealing with news articles, where LLM-generated texts resemble human texts in style, which opens up avenues for future research. ALHD establishes a foundation for research related to Arabic LLM-detection and mitigating risks of misinformation, academic dishonesty, and cyber threats.

Yufeng Li, Arkaitz Zubiaga

The rapid spread of misinformation on social media underscores the need for scalable fact-checking tools. A key step is claim detection, which identifies statements that can be objectively verified. Prior approaches often rely on linguistic cues or claim check-worthiness, but these struggle with vague political discourse and diverse formats such as tweets. We present RAVE (Retrieval and Scoring Aware Verifiable Claim Detection), a framework that combines evidence retrieval with structured signals of relevance and source credibility. Experiments on CT22-test and PoliClaim-test show that RAVE consistently outperforms text-only and retrieval-based baselines in both accuracy and F1.

Shaz Furniturewala, Arkaitz Zubiaga

The volume of machine-generated content online has grown dramatically due to the widespread use of Large Language Models (LLMs), leading to new challenges for content moderation systems. Conventional content moderation classifiers, which are usually trained on text produced by humans, suffer from misclassifications due to LLM-generated text deviating from their training data and adversarial attacks that aim to avoid detection. Present-day defence tactics are reactive rather than proactive, since they rely on adversarial training or external detection models to identify attacks. In this work, we aim to identify the vulnerable components of toxicity classifiers that contribute to misclassification, proposing a novel strategy based on mechanistic interpretability techniques. Our study focuses on fine-tuned BERT and RoBERTa classifiers, testing on diverse datasets spanning a variety of minority groups. We use adversarial attacking techniques to identify vulnerable circuits. Finally, we suppress these vulnerable circuits, improving performance against adversarial attacks. We also provide demographic-level insights into these vulnerable circuits, exposing fairness and robustness gaps in model training. We find that models have distinct heads that are either crucial for performance or vulnerable to attack and suppressing the vulnerable heads improves performance on adversarial input. We also find that different heads are responsible for vulnerability across different demographic groups, which can inform more inclusive development of toxicity detection models.

Raneem Alharthi, Rajwa Alharthi, Aiqi Jiang et al.

Abusive language detection has become an increasingly important task as a means to tackle this type of harmful content in social media. There has been a substantial body of research developing models for determining if a social media post is abusive or not; however, this research has primarily focused on exploiting social media posts individually, overlooking additional context that can be derived from surrounding posts. In this study, we look at conversational exchanges, where a user replies to an earlier post by another user (the parent tweet). We ask: does leveraging context from the parent tweet help determine if a reply post is abusive or not, and what are the features that contribute the most? We study a range of content-based and account-based features derived from the context, and compare this to the more widely studied approach of only looking at the features from the reply tweet. For a more generalizable study, we test four different classification models on a dataset made of conversational exchanges (parent-reply tweet pairs) with replies labeled as abusive or not. Our experiments show that incorporating contextual features leads to substantial improvements compared to the use of features derived from the reply tweet only, confirming the importance of leveraging context. We observe that, among the features under study, it is especially the content-based features (what is being posted) that contribute to the classification performance rather than account-based features (who is posting it). While using content-based features, it is best to combine a range of different features to ensure improved performance over being more selective and using fewer features. Our study provides insights into the development of contextualized abusive language detection models in realistic settings involving conversations.

Amani S. Abumansour, Arkaitz Zubiaga

Selecting check-worthy claims for fact-checking is considered a crucial part of expediting the fact-checking process by filtering out and ranking the check-worthy claims for being validated among the impressive amount of claims could be found online. The check-worthy claim detection task, however, becomes more challenging when the model needs to deal with new topics that differ from those seen earlier. In this study, we propose a domain-adaptation framework for check-worthy claims detection across topics for the Arabic language to adopt a new topic, mimicking a real-life scenario of the daily emergence of events worldwide. We propose the Gradual Topic Learning (GTL) model, which builds an ability to learning gradually and emphasizes the check-worthy claims for the target topic during several stages of the learning process. In addition, we introduce the Similarity-driven Gradual Topic Learning (SGTL) model that synthesizes gradual learning with a similarity-based strategy for the target topic. Our experiments demonstrate the effectiveness of our proposed model, showing an overall tendency for improving performance over the state-of-the-art baseline across 11 out of the 14 topics under study.

Bharathi A, Arkaitz Zubiaga

Stance detection has been widely studied as the task of determining if a social media post is positive, negative or neutral towards a specific issue, such as support towards vaccines. Research in stance detection has however often been limited to a single language and, where more than one language has been studied, research has focused on few-shot settings, overlooking the challenges of developing a zero-shot cross-lingual stance detection model. This paper makes the first such effort by introducing a novel approach to zero-shot cross-lingual stance detection, Multilingual Translation-Augmented BERT (MTAB), aiming to enhance the performance of a cross-lingual classifier in the absence of explicit training data for target languages. Our technique employs translation augmentation to improve zero-shot performance and pairs it with adversarial learning to further boost model efficacy. Through experiments on datasets labeled for stance towards vaccines in four languages English, German, French, Italian. We demonstrate the effectiveness of our proposed approach, showcasing improved results in comparison to a strong baseline model as well as ablated versions of our model. Our experiments demonstrate the effectiveness of model components, not least the translation-augmented data as well as the adversarial learning component, to the improved performance of the model. We have made our source code accessible on GitHub.

Peiling Yi, Arkaitz Zubiaga

Swear words are a common proxy to collect datasets with cyberbullying incidents. Our focus is on measuring and mitigating biases derived from spurious associations between swear words and incidents occurring as a result of such data collection strategies. After demonstrating and quantifying these biases, we introduce ID-XCB, the first data-independent debiasing technique that combines adversarial training, bias constraints and debias fine-tuning approach aimed at alleviating model attention to bias-inducing words without impacting overall model performance. We explore ID-XCB on two popular session-based cyberbullying datasets along with comprehensive ablation and generalisation studies. We show that ID-XCB learns robust cyberbullying detection capabilities while mitigating biases, outperforming state-of-the-art debiasing methods in both performance and bias mitigation. Our quantitative and qualitative analyses demonstrate its generalisability to unseen data.

Amikul Kalra, Arkaitz Zubiaga

Through anonymisation and accessibility, social media platforms have facilitated the proliferation of hate speech, prompting increased research in developing automatic methods to identify these texts. This paper explores the classification of sexism in text using a variety of deep neural network model architectures such as Long-Short-Term Memory (LSTMs) and Convolutional Neural Networks (CNNs). These networks are used in conjunction with transfer learning in the form of Bidirectional Encoder Representations from Transformers (BERT) and DistilBERT models, along with data augmentation, to perform binary and multiclass sexism classification on the dataset of tweets and gabs from the sEXism Identification in Social neTworks (EXIST) task in IberLEF 2021. The models are seen to perform comparatively to those from the competition, with the best performances seen using BERT and a multi-filter CNN model. Data augmentation further improves these results for the multi-class classification task. This paper also explores the errors made by the models and discusses the difficulty in automatically classifying sexism due to the subjectivity of the labels and the complexity of natural language used in social media.

Teodor Tiţa, Arkaitz Zubiaga

Hate speech detection within a cross-lingual setting represents a paramount area of interest for all medium and large-scale online platforms. Failing to properly address this issue on a global scale has already led over time to morally questionable real-life events, human deaths, and the perpetuation of hate itself. This paper illustrates the capabilities of fine-tuned altered multi-lingual Transformer models (mBERT, XLM-RoBERTa) regarding this crucial social data science task with cross-lingual training from English to French, vice-versa and each language on its own, including sections about iterative improvement and comparative error analysis.

Xia Zeng, Amani S. Abumansour, Arkaitz Zubiaga

As online false information continues to grow, automated fact-checking has gained an increasing amount of attention in recent years. Researchers in the field of Natural Language Processing (NLP) have contributed to the task by building fact-checking datasets, devising automated fact-checking pipelines and proposing NLP methods to further research in the development of different components. This paper reviews relevant research on automated fact-checking covering both the claim detection and claim validation components.

Dimitris Gkoumas, Bo Wang, Adam Tsakalidis et al.

Dementia affects cognitive functions of adults, including memory, language, and behaviour. Standard diagnostic biomarkers such as MRI are costly, whilst neuropsychological tests suffer from sensitivity issues in detecting dementia onset. The analysis of speech and language has emerged as a promising and non-intrusive technology to diagnose and monitor dementia. Currently, most work in this direction ignores the multi-modal nature of human communication and interactive aspects of everyday conversational interaction. Moreover, most studies ignore changes in cognitive status over time due to the lack of consistent longitudinal data. Here we introduce a novel fine-grained longitudinal multi-modal corpus collected in a natural setting from healthy controls and people with dementia over two phases, each spanning 28 sessions. The corpus consists of spoken conversations, a subset of which are transcribed, as well as typed and written thoughts and associated extra-linguistic information such as pen strokes and keystrokes. We present the data collection process and describe the corpus in detail. Furthermore, we establish baselines for capturing longitudinal changes in language across different modalities for two cohorts, healthy controls and people with dementia, outlining future research directions enabled by the corpus.

Rabab Alkhalifa, Arkaitz Zubiaga

Social media platforms provide a goldmine for mining public opinion on issues of wide societal interest and impact. Opinion mining is a problem that can be operationalised by capturing and aggregating the stance of individual social media posts as supporting, opposing or being neutral towards the issue at hand. While most prior work in stance detection has investigated datasets that cover short periods of time, interest in investigating longitudinal datasets has recently increased. Evolving dynamics in linguistic and behavioural patterns observed in new data require adapting stance detection systems to deal with the changes. In this survey paper, we investigate the intersection between computational linguistics and the temporal evolution of human communication in digital media. We perform a critical review of emerging research considering dynamics, exploring different semantic and pragmatic factors that impact linguistic data in general, and stance in particular. We further discuss current directions in capturing stance dynamics in social media. We discuss the challenges encountered when dealing with stance dynamics, identify open challenges and discuss future directions in three key dimensions: utterance, context and influence.