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.
Topic modelling, as a well-established unsupervised technique, has found extensive use in automatically detecting significant topics within a corpus of documents. However, classic topic modelling approaches (e.g., LDA) have certain drawbacks, such as the lack of semantic understanding and the presence of overlapping topics. In this work, we investigate the untapped potential of large language models (LLMs) as an alternative for uncovering the underlying topics within extensive text corpora. To this end, we introduce a framework that prompts LLMs to generate topics from a given set of documents and establish evaluation protocols to assess the clustering efficacy of LLMs. Our findings indicate that LLMs with appropriate prompts can stand out as a viable alternative, capable of generating relevant topic titles and adhering to human guidelines to refine and merge topics. Through in-depth experiments and evaluation, we summarise the advantages and constraints of employing LLMs in topic extraction.
As Large Language Models (LLMs) become more proficient, their misuse in large-scale viral disinformation campaigns is a growing concern. This study explores the capability of ChatGPT to generate unconditioned claims about the war in Ukraine, an event beyond its knowledge cutoff, and evaluates whether such claims can be differentiated by human readers and automated tools from human-written ones. We compare war-related claims from ClaimReview, authored by IFCN-registered fact-checkers, and similar short-form content generated by ChatGPT. We demonstrate that ChatGPT can produce realistic, target-specific disinformation cheaply, fast, and at scale, and that these claims cannot be reliably distinguished by humans or existing automated tools.
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 annotators are only asked to provide a single label for each sample and annotator disagreement is discarded when a final hard label is decided through majority voting. We challenge this traditional approach, acknowledging that determining the appropriate label can be difficult due to the ambiguity and lack of context in the data samples. Rather than discarding the information from such ambiguous annotations, our soft label method makes use of them for training. Our findings indicate that additional annotator information, such as confidence, secondary label and disagreement, can be used to effectively generate soft labels. Training classifiers with these soft labels then leads to improved performance and calibration on the hard label test set.
This paper analyses two hitherto unstudied sites sharing state-backed disinformation, Reliable Recent News (rrn.world) and WarOnFakes (waronfakes.com), which publish content in Arabic, Chinese, English, French, German, and Spanish. We describe our content acquisition methodology and perform cross-site unsupervised topic clustering on the resulting multilingual dataset. We also perform linguistic and temporal analysis of the web page translations and topics over time, and investigate articles with false publication dates. We make publicly available this new dataset of 14,053 articles, annotated with each language version, and additional metadata such as links and images. The main contribution of this paper for the NLP community is in the novel dataset which enables studies of disinformation networks, and the training of NLP tools for disinformation detection.
The use of abusive language online has become an increasingly pervasive problem that damages both individuals and society, with effects ranging from psychological harm right through to escalation to real-life violence and even death. Machine learning models have been developed to automatically detect abusive language, but these models can suffer from temporal bias, the phenomenon in which topics, language use or social norms change over time. This study aims to investigate the nature and impact of temporal bias in abusive language detection across various languages and explore mitigation methods. We evaluate the performance of models on abusive data sets from different time periods. Our results demonstrate that temporal bias is a significant challenge for abusive language detection, with models trained on historical data showing a significant drop in performance over time. We also present an extensive linguistic analysis of these abusive data sets from a diachronic perspective, aiming to explore the reasons for language evolution and performance decline. This study sheds light on the pervasive issue of temporal bias in abusive language detection across languages, offering crucial insights into language evolution and temporal bias mitigation.
A crucial aspect of a rumor detection model is its ability to generalize, particularly its ability to detect emerging, previously unknown rumors. Past research has indicated that content-based (i.e., using solely source posts as input) rumor detection models tend to perform less effectively on unseen rumors. At the same time, the potential of context-based models remains largely untapped. The main contribution of this paper is in the in-depth evaluation of the performance gap between content and context-based models specifically on detecting new, unseen rumors. Our empirical findings demonstrate that context-based models are still overly dependent on the information derived from the rumors' source post and tend to overlook the significant role that contextual information can play. We also study the effect of data split strategies on classifier performance. Based on our experimental results, the paper also offers practical suggestions on how to minimize the effects of temporal concept drift in static datasets during the training of rumor detection methods.
Credibility signals represent a wide range of heuristics that are typically used by journalists and fact-checkers to assess the veracity of online content. Automating the task of credibility signal extraction, however, is very challenging as it requires high-accuracy signal-specific extractors to be trained, while there are currently no sufficiently large datasets annotated with all credibility signals. This paper investigates whether large language models (LLMs) can be prompted effectively with a set of 18 credibility signals to produce weak labels for each signal. We then aggregate these potentially noisy labels using weak supervision in order to predict content veracity. We demonstrate that our approach, which combines zero-shot LLM credibility signal labeling and weak supervision, outperforms state-of-the-art classifiers on two misinformation datasets without using any ground-truth labels for training. We also analyse the contribution of the individual credibility signals towards predicting content veracity, which provides new valuable insights into their role in misinformation detection.
Adapters and Low-Rank Adaptation (LoRA) are parameter-efficient fine-tuning techniques designed to make the training of language models more efficient. Previous results demonstrated that these methods can even improve performance on some classification tasks. This paper complements the existing research by investigating how these techniques influence the classification performance and computation costs compared to full fine-tuning when applied to multilingual text classification tasks (genre, framing, and persuasion techniques detection; with different input lengths, number of predicted classes and classification difficulty), some of which have limited training data. In addition, we conduct in-depth analyses of their efficacy across different training scenarios (training on the original multilingual data; on the translations into English; and on a subset of English-only data) and different languages. Our findings provide valuable insights into the applicability of the parameter-efficient fine-tuning techniques, particularly to complex multilingual and multilabel classification tasks.
The task of retrieving already debunked narratives aims to detect stories that have already been fact-checked. The successful detection of claims that have already been debunked not only reduces the manual efforts of professional fact-checkers but can also contribute to slowing the spread of misinformation. Mainly due to the lack of readily available data, this is an understudied problem, particularly when considering the cross-lingual task, i.e. the retrieval of fact-checking articles in a language different from the language of the online post being checked. This paper fills this gap by (i) creating a novel dataset to enable research on cross-lingual retrieval of already debunked narratives, using tweets as queries to a database of fact-checking articles; (ii) presenting an extensive experiment to benchmark fine-tuned and off-the-shelf multilingual pre-trained Transformer models for this task; and (iii) proposing a novel multistage framework that divides this cross-lingual debunk retrieval task into refinement and re-ranking stages. Results show that the task of cross-lingual retrieval of already debunked narratives is challenging and off-the-shelf Transformer models fail to outperform a strong lexical-based baseline (BM25). Nevertheless, our multistage retrieval framework is robust, outperforming BM25 in most scenarios and enabling cross-domain and zero-shot learning, without significantly harming the model's performance.