The latest generative large language models (LLMs) have found their application in data augmentation tasks, where small numbers of text samples are LLM-paraphrased and then used to fine-tune downstream models. However, more research is needed to assess how different prompts, seed data selection strategies, filtering methods, or model settings affect the quality of paraphrased data (and downstream models). In this study, we investigate three text diversity incentive methods well established in crowdsourcing: taboo words, hints by previous outlier solutions, and chaining on previous outlier solutions. Using these incentive methods as part of instructions to LLMs augmenting text datasets, we measure their effects on generated texts’ lexical diversity and downstream model performance. We compare the effects over 5 different LLMs, 6 datasets and 2 downstream models. We show that diversity is most increased by taboo words, but downstream model performance is highest with hints.

Automated disinformation generation is often listed as one of the risks of large language models (LLMs). The theoretical ability to flood the information space with disinformation content might have dramatic consequences for democratic societies around the world. This paper presents a comprehensive study of the disinformation capabilities of the current generation of LLMs to generate false news articles in English language. In our study, we evaluated the capabilities of 10 LLMs using 20 disinformation narratives. We evaluated several aspects of the LLMs: how well they are at generating news articles, how strongly they tend to agree or disagree with the disinformation narratives, how often they generate safety warnings, etc. We also evaluated the abilities of detection models to detect these articles as LLM-generated. We conclude that LLMs are able to generate convincing news articles that agree with dangerous disinformation narratives.

There is a lack of research into capabilities of recent LLMs to generate convincing text in languages other than English and into performance of detectors of machine-generated text in multilingual settings. This is also reflected in the available benchmarks which lack authentic texts in languages other than English and predominantly cover older generators. To fill this gap, we introduce MULTITuDE, a novel benchmarking dataset for multilingual machine-generated text detection comprising of 74,081 authentic and machine-generated texts in 11 languages (ar, ca, cs, de, en, es, nl, pt, ru, uk, and zh) generated by 8 multilingual LLMs. Using this benchmark, we compare the performance of zero-shot (statistical and black-box) and fine-tuned detectors. Considering the multilinguality, we evaluate 1) how these detectors generalize to unseen languages (linguistically similar as well as dissimilar) and unseen LLMs and 2) whether the detectors improve their performance when trained on multiple languages.

Fact-checkers are often hampered by the sheer amount of online content that needs to be fact-checked. NLP can help them by retrieving already existing fact-checks relevant to the content being investigated. This paper introduces a new multilingual dataset for previously fact-checked claim retrieval. We collected 28k posts in 27 languages from social media, 206k fact-checks in 39 languages written by professional fact-checkers, as well as 31k connections between these two groups. This is the most extensive and the most linguistically diverse dataset of this kind to date. We evaluated how different unsupervised methods fare on this dataset and its various dimensions. We show that evaluating such a diverse dataset has its complexities and proper care needs to be taken before interpreting the results. We also evaluated a supervised fine-tuning approach, improving upon the unsupervised method significantly.

In this paper, we present neural model architecture submitted to the SemEval-2019 Task 9 competition: “Suggestion Mining from Online Reviews and Forums”. We participated in both subtasks for domain specific and also cross-domain suggestion mining. We proposed a recurrent neural network architecture that employs Bi-LSTM layers and also self-attention mechanism. Our architecture tries to encode words via word representation using ELMo and ensembles multiple models to achieve better results. We highlight importance of pre-processing of user-generated samples and its contribution to overall results. We performed experiments with different setups of our proposed model involving weighting of prediction classes for loss function. Our best model achieved in official test evaluation score of 0.6816 for subtask A and 0.6850 for subtask B. In official results, we achieved 12th and 10th place in subtasks A and B, respectively.

Using different neural network architectures is widely spread for many different NLP tasks. Unfortunately, most of the research is performed and evaluated only in English language and minor languages are often omitted. We believe using similar architectures for other languages can show interesting results. In this paper, we present our study on methods for improving sentiment classification in Slovak language. We performed several experiments for two different datasets, one containing customer reviews, the other one general Twitter posts. We show comparison of performance of different neural network architectures and also different word representations. We show that another improvement can be achieved by using a model ensemble. We performed experiments utilizing different methods of model ensemble. Our proposed models achieved better results than previous models for both datasets. Our experiments showed also other potential research areas.

Growing amount of comments make online discussions difficult to moderate by human moderators only. Antisocial behavior is a common occurrence that often discourages other users from participating in discussion. We propose a neural network based method that partially automates the moderation process. It consists of two steps. First, we detect inappropriate comments for moderators to see. Second, we highlight inappropriate parts within these comments to make the moderation faster. We evaluated our method on data from a major Slovak news discussion platform.

In this paper, we present neural models submitted to Shared Task on Implicit Emotion Recognition, organized as part of WASSA 2018. We propose a Bi-LSTM architecture with regularization through dropout and Gaussian noise. Our models use three different embedding layers: GloVe word embeddings trained on Twitter dataset, ELMo embeddings and also sentence embeddings. We see preprocessing as one of the most important parts of the task. We focused on handling emojis, emoticons, hashtags, and also various shortened word forms. In some cases, we proposed to remove some parts of the text, as they do not affect emotion of the original sentence. We also experimented with other modifications like category weights for learning and stacking multiple layers. Our model achieved a macro average F1 score of 65.55%, significantly outperforming the baseline model produced by a simple logistic regression.