Applying Large Language Models (LLMs) to high-stakes classification tasks like systematic review screening is challenged by prompt sensitivity and a lack of transparency. We introduce IMAPR (Iterative Multi-signal Adaptive Prompt Refinement), a novel framework where a single LLM uses its own internal signals to iteratively refine its prompts, improving classification robustness and reliability. Unlike black-box optimizers that tune the prompts using only external scores, IMAPR is a white-box approach that diagnoses why a prediction failed using three internal signals: model confidence, a rationale, and a knowledge alignment score that checks whether the evidence cited in the rationale actually covers the user-defined inclusion criteria. We evaluate IMAPR on a real-world biomedical screening task, comparing it against strong baselines including GPO and StraGo. IMAPR outperforms the best baseline (GPO) by 8.8% in Macro-F1 while maintaining high, stable recall across runs. Across seven LLMs, IMAPR yields an average 9.2% improvement in Macro-F1 An ablation shows that knowledge-alignment acts as a recall safeguard: removing it leaves Macro-F1 similar but degrades recall, reducing reliability for screening. These results suggest that diagnostic, signal-driven prompt refinement is a practical alternative to black-box optimization for transparent, dependable LLM screening systems.

The main way large language models (LLMs) learn to represent and interpret various experiences is through the process of supervised fine-tuning (SFT). However, current practices are not designed to be inclusive for people with ADHD, which leads to generative hermeneutical ignorance due to misrepresentation. Several ADHD characteristics clash with modern annotation task structures, so those voices remain underrepresented. We performed a literature-driven gap analysis, derived five design requirements and evaluation criteria and built an annotation interface that embodied those requirements. Consequently, a mixed approach user study with seven self-identified ADHD participants was conducted to measure behavioral metrics and collect post-task reflections. The results indicated that three of five design criteria were met, which is promising. However, the average mislabeling rate remained quite high, meaning that accuracy is still an open issue. Finally, our study demonstrated that small design adjustments accommodate a more diverse annotator pool, thus, we offer a framework that can be used to reinforce hermeneutical epistemic justice in annotation practices.

Generative AI can contribute to the misunderstanding or erasure of marginalized groups due to the insufficient nuanced data on their lived experiences. This limits the shared un- derstanding of their perspectives and contributes to a phenomenon called hermeneutical epistemic injustice. This study seeks to reduce this injustice by enabling real-life users from these groups to provide feedback that corrects the behavior of the model. However, victims of hermeneutical injustice struggle with articulating themselves, and current prac- tices lack sufficient support for user expression. Overcoming these challenges, we designed an interface to enable users to give feedback on the accuracy of the model, supported by a data processing workflow to ensure feasibility and scalability. We conducted a user study with 8 individuals with ADHD to evaluate whether the interface facilitates the extraction of accurate data, and found that it enables users to provide more concrete and precise feedback than existing methods, as it includes more guidance and control for the user.

This study investigates how hermeneutical injustices can become encoded in the Reinforcement Learning from Human Feedback processes used to fine-tune large language models (LLMs). While current research on fairness in LLMs has focused on bias and fairness, there remains a significant gap concerning subtler harms such as hermeneutical injustice. Using adults diagnosed with ADHD as a case study, this research explores how their unique communication and cognitive patterns may be misrepresented or excluded from the RLHF pipeline. The research adopts a qualitative literature review methodology, focusing specifically on real-world RLHF implementations by AI companies. The RLHF pipeline was divided into stages of human feedback collection, reward modeling, and policy optimization. Then, these stages of the RLHF were analyzed through the lens of hermeneutical injustice using interpretive desiderata: representation, flexibility, and authenticity. The findings highlight several conceptual risks. Limited annotator diversity and restrictive feedback formats may exclude neurodivergent voices. Reward models can unintentionally suppress atypical expressions, while policy optimization strategies, especially those prone to mode collapse, can erase some communication styles. Overall, the study shows that without deliberate attention to epistemic inclusion, RLHF processes may perpetuate hermeneutical injustices and undermining the epistemic fairness of LLMs.

This study investigates how large language models (LLMs) narrate ADHD-related experiences and whether their narrative forms give rise to hermeneutical injustice. Rather than comparing experience itself, this study analyzes how experiences are narrated. Using a hybrid coding strategy based on Reflexive Thematic Analysis, it compares LLM-generated outputs with first-person narratives from ADHD communities. The analysis identifies several recurring misnarration patterns, Truncated Subjectivity, One-Way Definition, Illocutionary Disablement, and Skewed Style Replacement. Each of these patterns constrains the interpretive space for expressing ADHD experience. Sub-themes are developed to further reveal injustice embedded in LLMs. These patterns are linked to both the training data and the optimization process. In addition, the underlying mechanism of LLMs lacks the différance structure that characterizes human narration.

Large Language Models are increasingly integrated into everyday applications, but their responses often reflect dominant cultural narratives, which can lead to misrepresentation of marginalized communities. This paper addresses the underexplored issue of hermeneutical epistemic injustice (HEI) in LLM outputs, particularly how these systems fail to accurately represent the lived experiences of people with ADHD when answering causal questions, and whether different prompting techniques can influence and improve the justice reflected in their responses. We introduce a practical framework for measuring HEI based on four proxies: intelligibility, conceptual fit, recognition of structural barriers, and expression style. Through a within-subjects user study with seven adults with ADHD, we evaluated three prompting strategies: Vanilla (baseline), Step-Back, and Human Persona + System 2. Our findings show that Human Persona + System 2 prompting stood out for its empathetic tone, balanced perspectives, and non-judgmental framing, thereby improving fairness across multiple HEI dimensions. Surprisingly, Vanilla prompts performed comparably well overall, while Step-Back responses offered clear practical information and contextual relevance, but were limited by an impassive, matter-of-fact tone. These results suggest that prompt design can meaningfully affect how well LLMs represent marginalized experiences. We conclude that advancing epistemic justice in generative AI requires thoughtful prompt design and may benefit from deeper engagement with affected communities to more accurately and respectfully represent their realities.

The use of research assistants has increased significantly, providing support and automation for researchers. However, there is limited research on researchers using research assistants and what assistance researchers require for each research stage.
We interview researchers to gather insights into their opinions and usage, and afterwards develop a prototype. Researchers highlight that the most difficult part of research is the experiment design, which is reflected in the lack of literature.
Participants use research assistants for reading literature and writing, but request more support. The research assistant must be factual, transparent, and correct, and including a conversation allows for feedback and discussion.
We evaluate the prototype for the experiment design phase, highlighting the effectiveness of the component architecture by generating correct experiments.

This thesis addresses the semantic gap in visual understanding, improving visual models with semantic reasoning capabilities so they can handle tasks like image captioning, question-answering, and scene understanding. The main focus is on integrating visual and textual data, leveraging human cognitive insights, and developing a robust multi-modal foundation model. The research starts with the exploration of multi-modal data integration to enhance semantic and contextual reasoning in fine-grained scene recognition. The proposed multi-modal models, which combine visual and textual inputs, outperform traditional models that rely solely on visuals. This is particularly true in complex urban environments where visual ambiguities often occur. This method emphasizes the significance of semantic enrichment through multi-modal integration, which helps resolve visual ambiguities and improve scene understanding.

Large language models (LLMs) are widely used tools that assist us by answering various questions. Humans implicitly use contrast as a natural way to think about and seek explanations (i.e., "Why A and not B?"). Explainability is a challenging aspect of LLMs, as we do not truly understand how good the LLM answers are. The challenge is understanding to what extent LLMs can generate effective contrastive self-explanations for users. We introduce the Contrastive Self-Explanation Method (CoSEM) to narrow the gap between LLMs and explainability. It generates contrastive self- explanations and evaluates them through automation and a user study on generality, usefulness, readability, and relevance. Our results indicate that LLMs are capable of generating effective contrastive self-explanations. Lexical analysis of contrastive explanation indicates that explanations are not less general than the text those explain, and semantic analysis shows that more complex models generalize self-explanations more consistently. Although it is challenging to evaluate contrast in self-explanations semantically, user study shows that some models (Llama3-8B) help understand the contrast. Moreover, task selection affects how readable users find the explanations, where more self-explanations on general topics (movie reviews) are more readable than more specific topics (medical diagnoses). Lastly, some models, such as Llama3-8B, excel at generating contrastive self-explanations that contain relevant information regarding input text.

User feedback plays a significant role in helping recommendation systems to make personalized and accurate predictions. Despite the fact that many methods of collecting user feedback have been proposed, little research exists that addresses both the breadth and depth of data collected. In this study, we incorporate personal reflection into traditional crowdsourcing tasks and investigate how it facilitates people's reflection on their usage of YouTube. We present a novel crowdsourcing approach with personal reflection integration based on several design principles, which allows participants to reflect on contextual factors and personal values of using YouTube through guided context recall and evaluations, therefore gathering deeper insights into people's preferences and behaviors on a large scale. We conducted a user study involving 20 participants and explored the insights generated from their textual answers and the role of design principles in the reflection process. This approach successfully enables multiple participants to conduct the study simultaneously, thereby reflecting on their watching behaviors and preferences. Based on the quantitative and qualitative analysis of the findings, we sum up the implications of this approach to provide guidance for the YouTube recommendation system and point to the directions for the design of similar studies in the future.

This thesis investigates the enhancement of sentence decomposition in Large Language Models (LLMs) through the integration of linguistic features, including constituency parsing, dependency parsing, and abstract meaning representation. Traditional decomposition methods, which often rely on rule-based approaches, struggle with highly intricate sentences. By incorporating detailed linguistic features and employing reasoning steps and supervision in prompts, we aim to improve the comprehension and decomposition capabilities of LLMs. Experimental results show that integrating these linguistic features has the potential to improve decomposition performance. However, these enhancements also introduce new error types and increase computational costs. This study identifies several error types in the programs generated by LLMs, including format, decomposition, and conversion errors, emphasizing the need for further refinement in model training and prompt design. This research lays a step toward more accurate and efficient processing of complex sentences in LLMs, encouraging ongoing development and optimization in this field.

With the advent of large language models (LLMs), developing solutions for Natural Language Processing (NLP) tasks has become more approachable. However, these models are opaque, which presents several challenges, such as prompt engineering, quality assessment, and error analysis. Explainability methods can have several potential benefits, such as improving accuracy, increasing trust, and assessing quality. However, limited research exists on how explainability techniques can be applied to LLMs in practice, particularly using human-centred methodologies. Therefore, this study takes a user-centered approach, investigating the needs and challenges of the NLP data scientist and developing an explainability tool to address these needs. This approach is done by conducting a formative study to deepen our understanding of the user, combined with relevant literature. The observations from the formative study were used to develop a tool tailored to the user’s specific needs. This development was done by creating requirements and a design based on the findings of the formative study, followed by a proof of concept implementation. User satisfaction was assessed through practical interviews with a fairness dataset, providing insights into the usefulness and usability of the explanation techniques and the tool. The tool implements three explanation techniques: uncertainty, token-level feature attribution, and contrastive explanations. These can be viewed using a web application separated from the Python development environment, making it easy to interact with. Other key features are that it can be easily integrated into the user’s existing workflow, is usable in practice and can be presented to different stakeholders within the project. The evaluation concluded that the tool fits the workflow and does indeed help the NLP data scientist to understand the model. However, the evaluation also showed that the explainability techniques did not provide the necessary insights to achieve the user’s goal, mainly to improve the model’s accuracy and make the error analysis actionable. More research should be done to see which other explainability techniques could provide insights that would lead to objectively better performance of these models. Finally, more explainability techniques should be developed that do not focus on debugging the model but rather on revealing its behaviour and thus providing a better understanding of how to improve it.

Summarising patient interactions creates a huge workload for the healthcare professionals. This research finds that patient interactions contain a lot of noise that is subjective of nature. To explore the problem area interviews with a summarisation prototype have been conducted to extract system requirements and validate those by implementing them in the prototype. Filtering noise, reinforcement learning and numerical factual correctness are of paramount importance to a successful summarisation system.

With the rapid development of Artificial Intelligence (AI), the size and complexity of models are increasing rapidly. The limited memory and computing power of microcontroller units (MCUs) pose significant challenges for running AI applications on them. This thesis presents a method to run deep learning models on MCUs using a distributed approach.

First, we identified memory size as the primary constraint for implementing deep learning models in MCUs. To address this issue, our method involves splitting the models into smaller weight fragments distributed across multiple networked MCUs. A coordinator MCU manages the overall process, including neuron mapping and data relaying. We demonstrated that our approach reduces peak RAM usage during inference compared to existing methods.

For optimization, we employed layer fusion and quantization to reduce model size while preserving accuracy. We also introduced a rating system to assign capability scores to MCUs for efficient task allocation, explained through mathematical equations.

Our simulation phase validated the effectiveness of our method, showing successful distributed inference in MCUs and providing insights for real-world applications. Implementation on a network of MCUs confirmed the practical applicability and efficiency of our approach.

In conclusion, this thesis presents a feasible and efficient distributed inference method for networked MCUs, addressing resource limitations and enabling practical AI applications on constrained MCU platforms.

Algorithms have a more prominent presence than ever in the domain of recruitment. Many different tasks ranging from finding candidates to scanning resumes are handled more and more by algorithms and less by humans. Automating these tasks has led to bias being exhibited towards different unprivileged groups, among these women. This has prompted a need to find solutions to this bias in order to achieve fairness in algorithms for everyone. This survey analyses the state of the literature on fairness and bias against women with a focus on recruitment algorithms. It has been found that a plethora of methods to achieve and measure fairness exist, with many of the technical methods having only been tested in a controlled environment and not in a production environment. Companies are not very forthcoming in sharing how they ensure fairness, which complicates the development of the field. There are many limitations to the current methods, however due to widespread usage of algorithms in the recruitment process, there is still a need for solutions to exist while these critiques are being addressed. It is vital for fairness to not only consider technical solutions, but also social solutions and to be aware of the limitations of each approach. Solving the issue of bias against women in algorithms requires sometimes realising that the best solution does not involve an algorithm at all, or in the case where an algorithm is applied, a critical engineer that is aware of the limitations and possibilities of different methods to achieve fairness. Future work is in addressing some major critiques of the current fairness literature and reducing the bias in society that often leads to algorithmic bias.

Algorithmic bias due to training from biased data is a widespread issue. Bias mitigation techniques such as fairness-oriented data pre-, in-, and post-processing can help but usually come at the cost of model accuracy. For this contribution, we first conducted a literature review to get a better insight into the potential trade-offs. We followed by implementing a Python program to test how the Disparate Impact Remover (DIR) pre-processing and Reject Option Classification (ROC) post-processing techniques impacted the fairness and accuracy metric values of a Logistic Regression model trained on data from the Adult Income dataset. The implementation also allows for building Pareto fronts that trade off fairness and accuracy metrics of choice, thus offering a blend of perspectives on fairness. Our findings give insight into how combined fairness methods influence the trade-off, but our implementation can be extended to explore such trade-offs using other datasets, models, and fairness methods.

This research investigates how biases in datasets influence the outputs of decision-making algorithms, specifically whether these biases are merely reflected or further amplified by the algorithms. Using the Adult/Census Income dataset from the UCI Machine Learning Repository, the research explores biases through the lens of three machine learning models: Logistic Regression, Decision Tree, and Random Forest. The analysis reveals that all models exhibit varying degrees of bias, dependent on the fairness metrics applied: Demographic Parity, Disparate Impact, Equal Opportunity, Equalized Odds. It has been found that higher accuracy does not necessarily equate to fairness. The findings emphasize the complex nature of algorithmic bias and the challenge of achieving fairness in automated decision-making systems. This research contributes to the understanding of bias amplification in algorithms and underscores the need for continued efforts to develop fairer decision-making systems in various sectors.

In the digital age, the proliferation of personal data within databases has made them prime targets for cyberattacks. As the volume of data increases, so does the frequency and sophistication of these attacks. This thesis investigates database security threats by deploying open source database honeypots to gather threat intelligence. We utilized five different honeypots at various interaction levels, deploying a total of 275 low-interaction, 50 medium-interaction, and 8 high-interaction honeypots over 20 to 23 days to collect a wide range of adversarial data. Through this deployment, we gathered 37, 618, 111 log entries from 8, 786 IPs.
Our analysis of these logs indicate that databases exposed to the internet are most likely to be dis-covered within an hour of deployment due to pervasive internet scanning. Additionally, we found that adversaries exhibit preferences for attacking certain database management systems, engage in irregular attack frequencies marked by short bursts, utilize diverse tools, and exploit both cloud service providers and infected machines. The findings also provide a high-level overview and analysis of observed attacks, including remote code execution, worms, botnets, data theft, and cryptojacking.

Large language models (LMs) are increasingly used in critical tasks, making it important that these models can be trusted. The confidence an LM assigns to its prediction is often used to indicate how much trust can be placed in that prediction. However, a high confidence can be incorrectly trusted if it turns out to be incorrect, also known as a high-confident error, or unknown unknown (UU). Blind spots, clusters of UUs, are caused by out-of-distribution data (OOD), bias, covariate shift, or unseen data. Previous work by Lippmann et al. generated samples based on these UUs, however, they selected a random subset of all found UUs. Although this was the first study that could mitigate blind spots without the need for crowd workers or oracles, they did not address the underlying causes of blind spots, such as OOD and bias. Data valuation is the research field that is concerned with valuing samples to improve model performance and can identify OOD data, bias, and noise. This paper proposed to combine the research field of data valuation, with the mitigation of blind spots. We generated synthetic samples using the highest-valued samples and retrained the LM using a Weighted Loss based on Data Values (WLDV). We conducted an extensive evaluation of our approach on four tasks, demonstrating a reduction of UUs by up to 32.7%, while retaining the same level of accuracy. This was the first exploration of combining the research fields of data valuation and blind spot mitigation.