Assessing the quality of group deliberation is essential for improving our understanding of deliberative processes. The Deliberative Reason Index (DRI) offers a sophisticated metric for evaluating group reasoning, but its implementation has been constrained by the complex and time-consuming process of statement generation. This thesis introduces an innovative, automated approach to DRI statement generation that leverages advanced natural language processing (NLP) and large language models (LLMs) to substantially reduce the human effort involved in survey preparation. Key contributions are a systematic framework for automated DRI statement generation and a methodological innovation that significantly lowers the barrier to conducting comprehensive deliberative process assessments. In addition, the findings provide a replicable template for integrating generative artificial intelligence into social science research methodologies.

Large Language Models (LLMs) are increasingly used to generate user-tailored summaries, adapting outputs to specific stakeholders. In legal contexts, this raises important questions about motivated reasoning -- how models strategically frame information to align with a stakeholder's position within the legal system. Building on theories of legal realism and recent trends in legal practice, we investigate how LLMs respond to prompts conditioned on different legal roles (e.g., judges, prosecutors, attorneys) when summarizing judicial decisions. We introduce an evaluation framework grounded in legal fact and reasoning inclusion, also considering favorability towards stakeholders. Our results show that even when prompts include balancing instructions, models exhibit selective inclusion patterns that reflect role-consistent perspectives. These findings raise broader concerns about how similar alignment may emerge as LLMs begin to infer user roles from prior interactions or context, even without explicit role instructions. Our results underscore the need for role-aware evaluation of LLM summarization behavior in high-stakes legal settings.

Participatory budgeting is a method of collectively understanding and addressing spending priorities where citizens vote on how a budget is spent, it is regularly run to improve the fairness of the distribution of public funds. Participatory budgeting requires voters to make decisions on projects which can lead to ``choice overload". A multi-agent reinforcement learning approach to decision support can make decision making easier for voters by identifying voting strategies that increase the winning proportion of their vote. This novel approach can also support policymakers by highlighting aspects of election design that enable fair compromise on projects. This paper presents a novel, ethically aligned approach to decision support using multi-agent deep reinforcement learning modelling. This paper introduces a novel use of a branching neural network architecture to overcome scalability challenges of multi-agent reinforcement learning in a decentralized way. Fair compromises are found through optimising voter actions towards greater representation of voter preferences in the winning set. Experimental evaluation with real-world participatory budgeting data reveals a pattern in fair compromise: that it is achievable through projects with smaller cost.

Background: Radiomics shows promise in characterizing glioblastoma, but its added value over clinical and molecular predictors has yet to be proven. This study assessed the added value of conventional radiomics (CR) and deep learning (DL) MRI radiomics for glioblastoma prognosis (<= 6 vs > 6 months survival) on a large multi-center dataset. Methods: After patient selection, our curated dataset gathers 1152 glioblastoma (WHO 2016) patients from five Swiss centers and one public source. It included clinical (age, gender), molecular (MGMT, IDH), and baseline MRI data (T1, T1 contrast, FLAIR, T2) with tumor regions. CR and DL models were developed using standard methods and evaluated on internal and external cohorts. Sub-analyses assessed models with different feature sets (imaging-only, clinical/molecular-only, combined-features) and patient subsets (S-1: all patients, S-2: with molecular data, S-3: IDH wildtype). Results: The best performance was observed in the full cohort (S-1). In external validation, the combined-feature CR model achieved an AUC of 0.75, slightly, but significantly outperforming clinical-only (0.74) and imaging-only (0.68) models. DL models showed similar trends, though without statistical significance. In S-2 and S-3, combined models did not outperform clinical-only models. Exploratory analysis of CR models for overall survival prediction suggested greater relevance of imaging data: across all subsets, combined-feature models significantly outperformed clinical-only models, though with a modest advantage of 2-4 C-index points. Conclusions: While confirming the predictive value of anatomical MRI sequences for glioblastoma prognosis, this multi-center study found standard CR and DL radiomics approaches offer minimal added value over demographic predictors such as age and gender.

We present a comprehensive investigation into plant bioelectric responses to human presence and emotional states, building on five years of systematic research. Using custom-built plant sensors and machine learning classification, we demonstrate that plants generate distinct bioelectric signals correlating with human proximity, emotional states, and physiological conditions. A deep learning model based on ResNet50 architecture achieved 97% accuracy in classifying human emotional states through plant voltage spectrograms, while control models with shuffled labels achieved only 30% accuracy. This study synthesizes findings from multiple experiments spanning 2020-2025, including individual recognition (66% accuracy), eurythmic gesture detection, stress prediction, and responses to human voice and movement. We propose that these phenomena represent evolved anti-herbivory early warning systems, where plants detect approaching animals through bioelectric field changes before physical contact. Our results challenge conventional understanding of plant sensory capabilities and suggest practical applications in agriculture, healthcare, and human-plant interaction research.

This paper presents two attack strategies designed to evade detection in ADMM-based systems by preventing significant changes to the residual during the attacked iteration. While many detection algorithms focus on identifying false data injection through residual changes, we show that our attacks remain undetected by keeping the residual largely unchanged. The first strategy uses a random starting point combined with Gram-Schmidt orthogonalization to ensure stealth, with potential for refinement by enhancing the orthogonal component to increase system disruption. The second strategy builds on the first, targeting financial gains by manipulating reactive power and pushing the system to its upper voltage limit, exploiting operational constraints. The effectiveness of the proposed attack-resilient mechanism is demonstrated through case studies on the IEEE 14-bus system. A comparison of the two strategies, along with commonly used naive attacks, reveals trade-offs between simplicity, detectability, and effectiveness, providing insights into ADMM system vulnerabilities. These findings underscore the need for more robust monitoring algorithms to protect against advanced attack strategies.

Machine learning and Bayesian optimization (BO) algorithms can significantly accelerate the optimization of chemical reactions. Transfer learning can bolster the effectiveness of BO algorithms in low-data regimes by leveraging pre-existing chemical information or data outside the direct optimization task (i.e., source data). Large language models (LLMs) have demonstrated that chemical information present in foundation training data can give them utility for processing chemical data. Furthermore, they can be augmented with and help synthesize potentially multiple modalities of source chemical data germane to the optimization task. In this work, we examine how chemical information from LLMs can be elicited and used for transfer learning to accelerate the BO of reaction conditions to maximize yield. Specifically, we show that a survey-like prompting scheme and preference learning can be used to infer a utility function which models prior chemical information embedded in LLMs over a chemical parameter space; we find that the utility function shows modest correlation to true experimental measurements (yield) over the parameter space despite operating in a zero-shot setting. Furthermore, we show that the utility function can be leveraged to focus BO efforts in promising regions of the parameter space, improving the yield of the initial BO query and enhancing optimization in 4 of the 6 datasets studied. Overall, we view this work as a step towards bridging the gap between the chemistry knowledge embedded in LLMs and the capabilities of principled BO methods to accelerate reaction optimization.

The aggressiveness of prostate cancer, the most common cancer in men worldwide, is primarily assessed based on histopathological data using the Gleason scoring system. While artificial intelligence (AI) has shown promise in accurately predicting Gleason scores, these predictions often lack inherent explainability, potentially leading to distrust in human-machine interactions. To address this issue, we introduce a novel dataset of 1,015 tissue microarray core images, annotated by an international group of 54 pathologists. The annotations provide detailed localized pattern descriptions for Gleason grading in line with international guidelines. Utilizing this dataset, we develop an inherently explainable AI system based on a U-Net architecture that provides predictions leveraging pathologists' terminology. This approach circumvents post-hoc explainability methods while maintaining or exceeding the performance of methods trained directly for Gleason pattern segmentation (Dice score: 0.713 $\pm$ 0.003 trained on explanations vs. 0.691 $\pm$ 0.010 trained on Gleason patterns). By employing soft labels during training, we capture the intrinsic uncertainty in the data, yielding strong results in Gleason pattern segmentation even in the context of high interobserver variability. With the release of this dataset, we aim to encourage further research into segmentation in medical tasks with high levels of subjectivity and to advance the understanding of pathologists' reasoning processes.

Scaling up deliberative and voting participation is a longstanding endeavor -- a cornerstone for direct democracy and legitimate collective choice. Recent breakthroughs in generative artificial intelligence (AI) and large language models (LLMs) provide unprecedented opportunities, but also alerting risks for digital democracy. AI personal assistants can overcome cognitive bandwidth limitations of humans, providing decision support capabilities or even direct AI representation of human voters at large scale. However, the quality of this representation and what underlying biases manifest when delegating collective decision making to LLMs is an alarming and timely challenge to tackle. By rigorously emulating with high realism more than >50K LLM voting personas in 81 real-world voting elections, we show that different LLMs (GPT 3, GPT 3.5, and Llama2) come with biases and significant inconsistencies in complex preferential ballot formats, compared to simpler and more consistent majoritarian elections. Strikingly, fair voting aggregation methods, such as equal shares, prove to be a win-win: fairer voting outcomes for humans with fairer AI representation. This novel underlying relationship proves paramount for democratic resilience in progressives scenarios with low voters turnout and voter fatigue supported by AI representatives: abstained voters are mitigated by recovering highly representative voting outcomes that are fairer. These insights provide remarkable foundations for science, policymakers and citizens in explaining and mitigating AI risks in democratic innovations.

Large Language Models (LLMs) have become integral to a wide spectrum of applications, ranging from traditional computing tasks to advanced artificial intelligence (AI) applications. This widespread adoption has spurred extensive research into LLMs across various disciplines, including the social sciences. Notably, studies have revealed that LLMs possess emotional intelligence, which can be further developed through positive emotional stimuli. This discovery raises an intriguing question: can negative emotions similarly influence LLMs, potentially enhancing their performance? In response to this question, we introduce NegativePrompt, a novel approach underpinned by psychological principles, involving ten specifically designed negative emotional stimuli. We embark on rigorous experimental evaluations of five LLMs including Flan-T5-Large, Vicuna, Llama 2, ChatGPT, and GPT-4, across a set of 45 tasks. The results are revealing: NegativePrompt markedly enhances the performance of LLMs, evidenced by relative improvements of 12.89% in Instruction Induction tasks and 46.25% in BIG-Bench tasks. Moreover, we conduct attention visualization experiments to decipher the underlying mechanisms of NegativePrompt's influence. Our research contributes significantly to the understanding of LLMs and emotion interaction, demonstrating the practical efficacy of NegativePrompt as an emotion-driven method and offering novel insights for the enhancement of LLMs in real-world applications. The code is available at https://github.com/wangxu0820/NegativePrompt.