This paper explores the application of large language models (LLMs) to extract nuanced and complex job features from unstructured job postings. Using a dataset of 1.2 million job postings provided by AdeptID, we developed a robust pipeline to identify and classify variables such as remote work availability, remuneration structures, educational requirements, and work experience preferences. Our methodology combines semantic chunking, retrieval-augmented generation (RAG), and fine-tuning DistilBERT models to overcome the limitations of traditional parsing tools. By leveraging these techniques, we achieved significant improvements in identifying variables often mislabeled or overlooked, such as non-salary-based compensation and inferred remote work categories. We present a comprehensive evaluation of our fine-tuned models and analyze their strengths, limitations, and potential for scaling. This work highlights the promise of LLMs in labor market analytics, providing a foundation for more accurate and actionable insights into job data.

Sentiment analysis is a widely researched area within Natural Language Processing (NLP), attracting significant interest due to the advent of automated solutions. Despite this, the task remains challenging because of the inherent complexity of languages and the subjective nature of sentiments. It is even more challenging for less-studied and less-resourced languages such as Lithuanian. Our review of existing Lithuanian NLP research reveals that traditional machine learning methods and classification algorithms have limited effectiveness for the task. In this work, we address sentiment analysis of Lithuanian five-star-based online reviews from multiple domains that we collect and clean. We apply transformer models to this task for the first time, exploring the capabilities of pre-trained multilingual Large Language Models (LLMs), specifically focusing on fine-tuning BERT and T5 models. Given the inherent difficulty of the task, the fine-tuned models perform quite well, especially when the sentiments themselves are less ambiguous: 80.74% and 89.61% testing recognition accuracy of the most popular one- and five-star reviews respectively. They significantly outperform current commercial state-of-the-art general-purpose LLM GPT-4. We openly share our fine-tuned LLMs online.

The classification of statements provided by individuals during police interviews is a complex and significant task within the domain of natural language processing (NLP) and legal informatics. The lack of extensive domain-specific datasets raises challenges to the advancement of NLP methods in the field. This paper aims to address some of the present challenges by introducing a novel dataset tailored for classification of statements made during police interviews, prior to court proceedings. Utilising the curated dataset for training and evaluation, we introduce a fine-tuned DistilBERT model that achieves state-of-the-art performance in distinguishing truthful from deceptive statements. To enhance interpretability, we employ explainable artificial intelligence (XAI) methods to offer explainability through saliency maps, that interpret the model's decision-making process. Lastly, we present an XAI interface that empowers both legal professionals and non-specialists to interact with and benefit from our system. Our model achieves an accuracy of 86%, and is shown to outperform a custom transformer architecture in a comparative study. This holistic approach advances the accessibility, transparency, and effectiveness of statement analysis, with promising implications for both legal practice and research.

Phishing email is a serious cyber threat that tries to deceive users by sending false emails with the intention of stealing confidential information or causing financial harm. Attackers, often posing as trustworthy entities, exploit technological advancements and sophistication to make detection and prevention of phishing more challenging. Despite extensive academic research, phishing detection remains an ongoing and formidable challenge in the cybersecurity landscape. Large Language Models (LLMs) and Masked Language Models (MLMs) possess immense potential to offer innovative solutions to address long-standing challenges. In this research paper, we present an optimized, fine-tuned transformer-based DistilBERT model designed for the detection of phishing emails. In the detection process, we work with a phishing email dataset and utilize the preprocessing techniques to clean and solve the imbalance class issues. Through our experiments, we found that our model effectively achieves high accuracy, demonstrating its capability to perform well. Finally, we demonstrate our fine-tuned model using Explainable-AI (XAI) techniques such as Local Interpretable Model-Agnostic Explanations (LIME) and Transformer Interpret to explain how our model makes predictions in the context of text classification for phishing emails.

In this note we use the State of the Union Address (SOTU) dataset from Kaggle to make some surprising (and some not so surprising) observations pertaining to the general timeline of American history, and the character and nature of the addresses themselves. Our main approach is using vector embeddings, such as BERT (DistilBERT) and GPT-2. While it is widely believed that BERT (and its variations) is most suitable for NLP classification tasks, we find out that GPT-2 in conjunction with nonlinear dimension reduction methods such as UMAP provide better separation and stronger clustering. This makes GPT-2 + UMAP an interesting alternative. In our case, no model fine-tuning is required, and the pre-trained out-of-the-box GPT-2 model is enough. We also used a fine-tuned DistilBERT model for classification detecting which President delivered which address, with very good results (accuracy 93% - 95% depending on the run). An analogous task was performed to determine the year of writing, and we were able to pin it down to about 4 years (which is a single presidential term). It is worth noting that SOTU addresses provide relatively small writing samples (with about 8'000 words on average, and varying widely from under 2'000 words to more than 20'000), and that the number of authors is relatively large (we used SOTU addresses of 42 US presidents). This shows that the techniques employed turn out to be rather efficient, while all the computations described in this note can be performed using a single GPU instance of Google Colab. The accompanying code is available on GitHub.

The field of Natural Language Processing which involves the use of artificial intelligence to support human languages has seen tremendous growth due to its high-quality features. Its applications such as language translation, chatbots, virtual assistants, search autocomplete, and autocorrect are widely used in various domains including healthcare, advertising, customer service, and target advertising. To provide pregnancy-related information a health domain chatbot has been proposed and this work explores two different NLP-based approaches for developing the chatbot. The first approach is a multiclass classification-based retrieval approach using BERTbased multilingual BERT and multilingual DistilBERT while the other approach employs a transformer-based generative chatbot for pregnancy-related information. The performance of both stemmed and non-stemmed datasets in Nepali language has been analyzed for each approach. The experimented results indicate that BERT-based pre-trained models perform well on non-stemmed data whereas scratch transformer models have better performance on stemmed data. Among the models tested the DistilBERT model achieved the highest training and validation accuracy and testing accuracy of 0.9165 on the retrieval-based model architecture implementation on the non-stemmed dataset. Similarly, in the generative approach architecture implementation with transformer 1 gram BLEU and 2 gram BLEU scores of 0.3570 and 0.1413 respectively were achieved.

Annotating costs of large corpora are still one of the main bottlenecks in empirical social science research. On the one hand, making use of the capabilities of domain transfer allows re-using annotated data sets and trained models. On the other hand, it is not clear how well domain transfer works and how reliable the results are for transfer across different dimensions. We explore the potential of domain transfer across geographical locations, languages, time, and genre in a large-scale database of political manifestos. First, we show the strong within-domain classification performance of fine-tuned transformer models. Second, we vary the genre of the test set across the aforementioned dimensions to test for the fine-tuned models' robustness and transferability. For switching genres, we use an external corpus of transcribed speeches from New Zealand politicians while for the other three dimensions, custom splits of the Manifesto database are used. While BERT achieves the best scores in the initial experiments across modalities, DistilBERT proves to be competitive at a lower computational expense and is thus used for further experiments across time and country. The results of the additional analysis show that (Distil)BERT can be applied to future data with similar performance. Moreover, we observe (partly) notable differences between the political manifestos of different countries of origin, even if these countries share a language or a cultural background.

The recent introduction of Transformers language representation models allowed great improvements in many natural language processing (NLP) tasks. However, if on one hand the performances achieved by this kind of architectures are surprising, on the other their usability is limited by the high number of parameters which constitute their network, resulting in high computational and memory demands. In this work we present BERTino, a DistilBERT model which proposes to be the first lightweight alternative to the BERT architecture specific for the Italian language. We evaluated BERTino on the Italian ISDT, Italian ParTUT, Italian WikiNER and multiclass classification tasks, obtaining F1 scores comparable to those obtained by a BERTBASE with a remarkable improvement in training and inference speed.

Flooding is one of the most destructive and costly natural disasters, and climate changes would further increase risks globally. This work presents a novel multimodal machine learning approach for multi-year global flood risk prediction, combining geographical information and historical natural disaster dataset. Our multimodal framework employs state-of-the-art processing techniques to extract embeddings from each data modality, including text-based geographical data and tabular-based time-series data. Experiments demonstrate that a multimodal approach, that is combining text and statistical data, outperforms a single-modality approach. Our most advanced architecture, employing embeddings extracted using transfer learning upon DistilBert model, achieves 75\%-77\% ROCAUC score in predicting the next 1-5 year flooding event in historically flooded locations. This work demonstrates the potentials of using machine learning for long-term planning in natural disaster management.

Using 19th-century newspapers as a case study, we extend the time-masking approach proposed by Rosin et al. [2022] and compare different strategies for inserting temporal, political and geographical information into a Masked Language Model. After fine-tuning several DistilBERT on enhanced input data, we provide a systematic evaluation of these models on a set of evaluation tasks: pseudo-perplexity, metadata mask-filling and supervised classification. We find that showing relevant metadata to a language model has a beneficial impact and may even produce more robust and fairer models.