Large language models (LLMs), such as ChatGPT, have rapidly penetrated into people's work and daily lives over the past few years, due to their extraordinary conversational skills and intelligence. ChatGPT has become the fastest-growing software in terms of user numbers in human history and become an important foundational model for the next generation of artificial intelligence applications. However, the generations of LLMs are not entirely reliable, often producing content with factual errors, biases, and toxicity. Given their vast number of users and wide range of application scenarios, these unreliable responses can lead to many serious negative impacts. This thesis introduces the exploratory works in the field of language model reliability during the PhD study, focusing on the correctness, non-toxicity, and fairness of LLMs from both software testing and natural language processing perspectives. First, to measure the correctness of LLMs, we introduce two testing frameworks, FactChecker and LogicAsker, to evaluate factual knowledge and logical reasoning accuracy, respectively. Second, for the non-toxicity of LLMs, we introduce two works for red-teaming LLMs. Third, to evaluate the fairness of LLMs, we introduce two evaluation frameworks, BiasAsker and XCulturalBench, to measure the social bias and cultural bias of LLMs, respectively.

The digitization of historical documents is crucial for preserving the cultural heritage of the society. An important step in this process is converting scanned images to text using Optical Character Recognition (OCR), which can enable further search, information extraction, etc. Unfortunately, this is a hard problem as standard OCR tools are not tailored to deal with historical orthography as well as with challenging layouts. Thus, it is standard to apply an additional text correction step on the OCR output when dealing with such documents. In this work, we focus on Bulgarian, and we create the first benchmark dataset for evaluating the OCR text correction for historical Bulgarian documents written in the first standardized Bulgarian orthography: the Drinov orthography from the 19th century. We further develop a method for automatically generating synthetic data in this orthography, as well as in the subsequent Ivanchev orthography, by leveraging vast amounts of contemporary literature Bulgarian texts. We then use state-of-the-art LLMs and encoder-decoder framework which we augment with diagonal attention loss and copy and coverage mechanisms to improve the post-OCR text correction. The proposed method reduces the errors introduced during recognition and improves the quality of the documents by 25\%, which is an increase of 16\% compared to the state-of-the-art on the ICDAR 2019 Bulgarian dataset. We release our data and code at \url{https://github.com/angelbeshirov/post-ocr-text-correction}.}

This paper introduces novel deep reinforcement learning (Deep-RL) techniques using parallel distributional actor-critic networks for navigating terrestrial mobile robots. Our approaches use laser range findings, relative distance, and angle to the target to guide the robot. We trained agents in the Gazebo simulator and deployed them in real scenarios. Results show that parallel distributional Deep-RL algorithms enhance decision-making and outperform non-distributional and behavior-based approaches in navigation and spatial generalization.

Climate models lack the necessary resolution for urban climate studies, requiring computationally intensive processes to estimate high resolution air temperatures. In contrast, Data-driven approaches offer faster and more accurate air temperature downscaling. This study presents a data-driven framework for downscaling air temperature using publicly available outputs from urban climate models, specifically datasets generated by UrbClim. The proposed framework utilized morphological features extracted from LiDAR data. To extract urban morphological features, first a three-dimensional building model was created using LiDAR data and deep learning models. Then, these features were integrated with meteorological parameters such as wind, humidity, etc., to downscale air temperature using machine learning algorithms. The results demonstrated that the developed framework effectively extracted urban morphological features from LiDAR data. Deep learning algorithms played a crucial role in generating three-dimensional models for extracting the aforementioned features. Also, the evaluation of air temperature downscaling results using various machine learning models indicated that the LightGBM model had the best performance with an RMSE of 0.352{\deg}K and MAE of 0.215{\deg}K. Furthermore, the examination of final air temperature maps derived from downscaling showed that the developed framework successfully estimated air temperatures at higher resolutions, enabling the identification of local air temperature patterns at street level. The corresponding source codes are available on GitHub: https://github.com/FatemehCh97/Air-Temperature-Downscaling.

In this work, we present Curled-Dreamer, a novel reinforcement learning algorithm that integrates contrastive learning into the DreamerV3 framework to enhance performance in visual reinforcement learning tasks. By incorporating the contrastive loss from the CURL algorithm and a reconstruction loss from autoencoder, Curled-Dreamer achieves significant improvements in various DeepMind Control Suite tasks. Our extensive experiments demonstrate that Curled-Dreamer consistently outperforms state-of-the-art algorithms, achieving higher mean and median scores across a diverse set of tasks. The results indicate that the proposed approach not only accelerates learning but also enhances the robustness of the learned policies. This work highlights the potential of combining different learning paradigms to achieve superior performance in reinforcement learning applications.

Kolmogorov-Arnold Networks (KANs) have shown potential as an alternative to Multi-Layer Perceptrons (MLPs) in neural networks, providing universal function approximation with fewer parameters and reduced memory usage. In this paper, we explore the use of KANs as function approximators within the Proximal Policy Optimization (PPO) algorithm. We evaluate this approach by comparing its performance to the original MLP-based PPO using the DeepMind Control Proprio Robotics benchmark. Our results indicate that the KAN-based reinforcement learning algorithm can achieve comparable performance to its MLP-based counterpart, often with fewer parameters. These findings suggest that KANs may offer a more efficient option for reinforcement learning models.

The digitisation of historical print media archives is crucial for increasing accessibility to contemporary records. However, the process of Optical Character Recognition (OCR) used to convert physical records to digital text is prone to errors, particularly in the case of newspapers and periodicals due to their complex layouts. This paper introduces Context Leveraging OCR Correction (CLOCR-C), which utilises the infilling and context-adaptive abilities of transformer-based language models (LMs) to improve OCR quality. The study aims to determine if LMs can perform post-OCR correction, improve downstream NLP tasks, and the value of providing the socio-cultural context as part of the correction process. Experiments were conducted using seven LMs on three datasets: the 19th Century Serials Edition (NCSE) and two datasets from the Overproof collection. The results demonstrate that some LMs can significantly reduce error rates, with the top-performing model achieving over a 60% reduction in character error rate on the NCSE dataset. The OCR improvements extend to downstream tasks, such as Named Entity Recognition, with increased Cosine Named Entity Similarity. Furthermore, the study shows that providing socio-cultural context in the prompts improves performance, while misleading prompts lower performance. In addition to the findings, this study releases a dataset of 91 transcribed articles from the NCSE, containing a total of 40 thousand words, to support further research in this area. The findings suggest that CLOCR-C is a promising approach for enhancing the quality of existing digital archives by leveraging the socio-cultural information embedded in the LMs and the text requiring correction.

Online AI decision-making algorithms are increasingly used by digital interventions to dynamically personalize treatment to individuals. These algorithms determine, in real-time, the delivery of treatment based on accruing data. The objective of this paper is to provide guidelines for enabling effective monitoring of online decision-making algorithms with the goal of (1) safeguarding individuals and (2) ensuring data quality. We elucidate guidelines and discuss our experience in monitoring online decision-making algorithms in two digital intervention clinical trials (Oralytics and MiWaves). Our guidelines include (1) developing fallback methods, pre-specified procedures executed when an issue occurs, and (2) identifying potential issues categorizing them by severity (red, yellow, and green). Across both trials, the monitoring systems detected real-time issues such as out-of-memory issues, database timeout, and failed communication with an external source. Fallback methods prevented participants from not receiving any treatment during the trial and also prevented the use of incorrect data in statistical analyses. These trials provide case studies for how health scientists can build monitoring systems for their digital intervention. Without these algorithm monitoring systems, critical issues would have gone undetected and unresolved. Instead, these monitoring systems safeguarded participants and ensured the quality of the resulting data for updating the intervention and facilitating scientific discovery. These monitoring guidelines and findings give digital intervention teams the confidence to include online decision-making algorithms in digital interventions.

The rapid decline in global biodiversity demands innovative conservation strategies. This paper examines the use of artificial intelligence (AI) in wildlife conservation, focusing on the Conservation AI platform. Leveraging machine learning and computer vision, Conservation AI detects and classifies animals, humans, and poaching-related objects using visual spectrum and thermal infrared cameras. The platform processes this data with convolutional neural networks (CNNs) and Transformer architectures to monitor species, including those which are critically endangered. Real-time detection provides the immediate responses required for time-critical situations (e.g. poaching), while non-real-time analysis supports long-term wildlife monitoring and habitat health assessment. Case studies from Europe, North America, Africa, and Southeast Asia highlight the platform's success in species identification, biodiversity monitoring, and poaching prevention. The paper also discusses challenges related to data quality, model accuracy, and logistical constraints, while outlining future directions involving technological advancements, expansion into new geographical regions, and deeper collaboration with local communities and policymakers. Conservation AI represents a significant step forward in addressing the urgent challenges of wildlife conservation, offering a scalable and adaptable solution that can be implemented globally.

This article provides a critical overview of the recently approved Artificial Intelligence Act. It starts by presenting the main structure, objectives, and approach of Regulation (EU) 2024/1689. A definition of key concepts follows, and then the material and territorial scope, as well as the timing of application, are analyzed. Although the Regulation does not explicitly set out principles, the main ideas of fairness, accountability, transparency, and equity in AI underly a set of rules of the regulation. This is discussed before looking at the ill-defined set of forbidden AI practices (manipulation and e exploitation of vulnerabilities, social scoring, biometric identification and classification, and predictive policing). It is highlighted that those rules deal with behaviors rather than AI systems. The qualification and regulation of high-risk AI systems are tackled, alongside the obligation of transparency for certain systems, the regulation of general-purpose models, and the rules on certification, supervision, and sanctions. The text concludes that even if the overall framework can be deemed adequate and balanced, the approach is so complex that it risks defeating its own purpose of promoting responsible innovation within the European Union and beyond its borders.