Event log analysis is an important task that security professionals undertake. Event logs record key information on activities that occur on computing devices, and due to the substantial number of events generated, they consume a large amount of time and resources to analyse. This demanding and repetitive task is also prone to errors. To address these concerns, researchers have developed automated techniques to improve the event log analysis process. Large Language Models (LLMs) have recently demonstrated the ability to successfully perform a wide range of tasks that individuals would usually partake in, to high standards, and at a pace and degree of complexity that outperform humans. Due to this, researchers are rapidly investigating the use of LLMs for event log analysis. This includes fine-tuning, Retrieval-Augmented Generation (RAG) and in-context learning, which affect performance. These works demonstrate good progress, yet there is a need to understand the developing body of knowledge, identify commonalities between works, and identify key challenges and potential solutions to further developments in this domain. This paper aims to survey LLM-based event log analysis techniques, providing readers with an in-depth overview of the domain, gaps identified in previous research, and concluding with potential avenues to explore in future.

Large language models are increasingly customized through fine-tuning and other adaptations, creating challenges in enforcing licensing terms and managing downstream impacts. Tracking model origins is crucial both for protecting intellectual property and for identifying derived models when biases or vulnerabilities are discovered in foundation models. We address this challenge by developing a framework for testing model provenance: Whether one model is derived from another. Our approach is based on the key observation that real-world model derivations preserve significant similarities in model outputs that can be detected through statistical analysis. Using only black-box access to models, we employ multiple hypothesis testing to compare model similarities against a baseline established by unrelated models. On two comprehensive real-world benchmarks spanning models from 30M to 4B parameters and comprising over 600 models, our tester achieves 90-95% precision and 80-90% recall in identifying derived models. These results demonstrate the viability of systematic provenance verification in production environments even when only API access is available.

Hierarchical Merging is a technique commonly used to summarize very long texts ($>$100K tokens) by breaking down the input into smaller sections, summarizing those sections individually, and then merging or combining those summaries into a final coherent summary. Although it helps address the limitations of large language models (LLMs) with fixed input length constraints, the recursive merging process can amplify LLM hallucinations, increasing the risk of factual inaccuracies. In this paper, we seek to mitigate hallucinations by enriching hierarchical merging with context from the source document. Specifically, we propose different approaches to contextual augmentation ranging from \emph{replacing} intermediate summaries with relevant input context, to \emph{refining} them while using the context as supporting evidence, and \emph{aligning} them implicitly (via citations) to the input. Experimental results on datasets representing legal and narrative domains show that contextual augmentation consistently outperforms zero-shot and hierarchical merging baselines for the Llama 3.1 model family. Our analysis further reveals that refinement methods tend to perform best when paired with extractive summarization for identifying relevant input.

Large Language Models (LLMs) are transforming how people find information, and many users turn nowadays to chatbots to obtain answers to their questions. Despite the instant access to abundant information that LLMs offer, it is still important to promote critical thinking and problem-solving skills. Automatic hint generation is a new task that aims to support humans in answering questions by themselves by creating hints that guide users toward answers without directly revealing them. In this context, hint evaluation focuses on measuring the quality of hints, helping to improve the hint generation approaches. However, resources for hint research are currently spanning different formats and datasets, while the evaluation tools are missing or incompatible, making it hard for researchers to compare and test their models. To overcome these challenges, we introduce HintEval, a Python library that makes it easy to access diverse datasets and provides multiple approaches to generate and evaluate hints. HintEval aggregates the scattered resources into a single toolkit that supports a range of research goals and enables a clear, multi-faceted, and reliable evaluation. The proposed library also includes detailed online documentation, helping users quickly explore its features and get started. By reducing barriers to entry and encouraging consistent evaluation practices, HintEval offers a major step forward for facilitating hint generation and analysis research within the NLP/IR community.

This thesis explores advanced approaches to improve explainability in computer vision by analyzing and modeling the features exploited by deep neural networks. Initially, it evaluates attribution methods, notably saliency maps, by introducing a metric based on algorithmic stability and an approach utilizing Sobol indices, which, through quasi-Monte Carlo sequences, allows a significant reduction in computation time. In addition, the EVA method offers a first formulation of attribution with formal guarantees via verified perturbation analysis. Experimental results indicate that in complex scenarios these methods do not provide sufficient understanding, particularly because they identify only "where" the model focuses without clarifying "what" it perceives. Two hypotheses are therefore examined: aligning models with human reasoning -- through the introduction of a training routine that integrates the imitation of human explanations and optimization within the space of 1-Lipschitz functions -- and adopting a conceptual explainability approach. The CRAFT method is proposed to automate the extraction of the concepts used by the model and to assess their importance, complemented by MACO, which enables their visualization. These works converge towards a unified framework, illustrated by an interactive demonstration applied to the 1000 ImageNet classes in a ResNet model.

The widespread prevalence of misinformation poses significant societal concerns. Out-of-context misinformation, where authentic images are paired with false text, is particularly deceptive and easily misleads audiences. Most existing detection methods primarily evaluate image-text consistency but often lack sufficient explanations, which are essential for effectively debunking misinformation. We present a model that detects multimodal misinformation through cross-modality consistency checks, requiring minimal training time. Additionally, we propose a lightweight model that achieves competitive performance using only one-third of the parameters. We also introduce a dual-purpose zero-shot learning task for generating contextualized warnings, enabling automated debunking and enhancing user comprehension. Qualitative and human evaluations of the generated warnings highlight both the potential and limitations of our approach.

As software systems become more complex and configurable, more performance problems tend to arise from the configuration designs. This has caused some configuration options to unexpectedly degrade performance which deviates from their original expectations designed by the developers. Such discrepancies, namely configuration performance bugs (CPBugs), are devastating and can be deeply hidden in the source code. Yet, efficiently testing CPBugs is difficult, not only due to the test oracle is hard to set, but also because the configuration measurement is expensive and there are simply too many possible configurations to test. As such, existing testing tools suffer from lengthy runtime or have been ineffective in detecting CPBugs when the budget is limited, compounded by inaccurate test oracle. In this paper, we seek to achieve significantly faster CPBug testing by neurally prioritizing the testing at both the configuration option and value range levels with automated oracle estimation. Our proposed tool, dubbed NDP, is a general framework that works with different heuristic generators. The idea is to leverage two neural language models: one to estimate the CPBug types that serve as the oracle while, more vitally, the other to infer the probabilities of an option being CPBug-related, based on which the options and the value ranges to be searched can be prioritized. Experiments on several widely-used systems of different versions reveal that NDP can, in general, better predict CPBug type in 87% cases and find more CPBugs with up to 88.88x testing efficiency speedup over the state-of-the-art tools.

In recent years, Large Language Models (LLMs) rapidly gained popularity across all parts of society, including education. After initial skepticism and bans, many schools have chosen to embrace this new technology by integrating it into their curricula in the form of virtual tutors and teaching assistants. However, neither the companies developing this technology nor the public institutions involved in its implementation have set up a formal system to collect feedback from the stakeholders impacted by them. In this paper, we argue that understanding the perceptions of those directly affected by LLMS in the classroom, such as students and teachers, as well as those indirectly impacted, like parents and school staff, is essential for ensuring responsible use of AI in this critical domain. Our contributions are two-fold. First, we present results of a literature review focusing on the perceptions of LLM-based chatbots in education. We highlight important gaps in the literature, such as the exclusion of key educational agents (e.g., parents or school administrators) when analyzing the role of stakeholders, and the frequent omission of the learning contexts in which the AI systems are implemented. Thus, we present a taxonomy that organizes existing literature on stakeholder perceptions. Second, we propose the Contextualized Perceptions for the Adoption of Chatbots in Education (Co-PACE) framework, which can be used to systematically elicit perceptions and inform whether and how LLM-based chatbots should be designed, developed, and deployed in the classroom.

Localization of radio frequency (RF) sources has critical applications, including search and rescue, jammer detection, and monitoring of hostile activities. Unmanned aerial vehicles (UAVs) offer significant advantages for RF source localization (RFSL) over terrestrial methods, leveraging autonomous 3D navigation and improved signal capture at higher altitudes. Recent advancements in deep learning (DL) have further enhanced localization accuracy, particularly for outdoor scenarios. DL models often face challenges in real-world performance, as they are typically trained on simulated datasets that fail to replicate real-world conditions fully. To address this, we first propose the Enhanced Two-Ray propagation model, reducing the simulation-to-reality gap by improving the accuracy of propagation environment modeling. For RFSL, we propose the 3D Cluster-Based RealAdaptRNet, a DL-based method leveraging 3D clustering-based feature extraction for robust localization. Experimental results demonstrate that the proposed Enhanced Two-Ray model provides superior accuracy in simulating real-world propagation scenarios compared to conventional free-space and two-ray models. Notably, the 3D Cluster-Based RealAdaptRNet, trained entirely on simulated datasets, achieves exceptional performance when validated in real-world environments using the AERPAW physical testbed, with an average localization error of 18.2 m. The proposed approach is computationally efficient, utilizing 33.5 times fewer parameters, and demonstrates strong generalization capabilities across diverse trajectories, making it highly suitable for real-world applications.

At 2.16pm California time last Sunday, the US billionaire tech investor Marc Andreessen called it. "DeepSeek R1 is AI's Sputnik moment," he posted on X. A Chinese startup, operating since 2023 and helmed by a millennial mathematician, had unveiled a new chatbot that seemed to equal the performance of America's leading models at a fraction of the cost. Never mind that its answers on everything from the status of Taiwan to the 1989 Tiananmen Square massacre were curbed by Chinese Communist party (CCP) censors. To Andreessen, a veteran of decades of technology booms and busts, it was like the Soviet Union getting the first satellite into orbit in 1957 and shocking America. The next day, shares in several of the world's biggest companies plunged – including the biggest fall in US market history for microchip maker Nvidia, which lost nearly 600bn.