Large language models (LLMs) trained with reinforcement objectives often achieve superficially correct answers via shortcut strategies, pairing correct outputs with spurious or unfaithful reasoning and degrading under small causal perturbations. We introduce Causally-Enhanced Policy Optimization (CE-PO), a drop-in reward-shaping framework that augments policy optimization with a differentiable proxy for causal coherence along the generation pathway from prompt (Z) to rationale (X) to answer (Y). CE-PO estimates model-internal influence with Jacobian-based sensitivities, counterfactually hardens these signals to suppress nuisance cues, and fuses the resulting coherence score with task-accuracy feedback via a Minkowski (power-mean) combiner, exposing a single tunable between accuracy and coherence trade-off. The unified reward integrates with PPO/GRPO without architectural changes. Across reasoning benchmarks and causal stress tests, CE-PO reduces reward hacking and unfaithful chain-of-thought while improving robustness to correlation-causation flips and light counterfactual edits, all at near-parity accuracy. Experimental results across 4 datasets show that CE-PO improves accuracy over baselines by 5.49% on average (up to 9.58%), while improving robustness to correlation-causation flips and light counterfactual edits.

However, the computational burden and ciphertext expansion associated with homomorphic encryption can significantly increase resource and communication overhead. T o address these challenges, we propose FedBit, a hardware/software co-designed framework optimized for the Brakerski-Fan-V ercauteren (BFV) scheme. FedBit employs bit-interleaved data packing to embed multiple model parameters into a single ciphertext coefficient, thereby minimizing ciphertext expansion and maximizing computational parallelism. Additionally, we integrate a dedicated FPGA accelerator to handle cryptographic operations and an optimized dataflow to reduce the memory overhead. Experimental results demonstrate that FedBit achieves a speedup of two orders of magnitude in encryption and lowers average communication overhead by 60.7%, while maintaining high accuracy.

Abstract--Large Language Models (LLMs) are increasingly susceptible to jailbreak attacks, which are adversarial prompts that bypass alignment constraints and induce unauthorized or harmful behaviors. These vulnerabilities undermine the safety, reliability, and trustworthiness of LLM outputs, posing critical risks in domains such as healthcare, finance, and legal compliance. In this paper, we propose GuardNet, a hierarchical filtering framework that detects and filters jailbreak prompts prior to inference. GuardNet constructs structured graphs that combine sequential links, syntactic dependencies, and attention-derived token relations to capture both linguistic structure and contextual patterns indicative of jailbreak behavior. It then applies graph neural networks at two levels: (i) a prompt-level filter that detects global adversarial prompts, and (ii) a token-level filter that pinpoints fine-grained adversarial spans. Extensive experiments across three datasets and multiple attack settings show that GuardNet substantially outperforms prior defenses. Despite its structural complexity, GuardNet maintains acceptable latency and generalizes well in cross-domain evaluations, making it a practical and robust defense against jailbreak threats in real-world LLM deployments. I. Introduction Large Language Models (LLMs) have become central to a wide range of applications, powering systems in domains such as education [1], healthcare [2], finance [3], law [4], and customer support [5]. Their ability to understand and generate human-like text has enabled automation of complex tasks such as legal reasoning, clinical triage, financial analysis, and policy drafting. However, this general-purpose capability also makes LLMs vulnerable to misuse. In particular, LLMs are highly susceptible to prompt-based adversarial attacks, especially jailbreak prompts [6], [7], which are carefully engineered inputs designed to bypass alignment constraints and elicit unauthorized or harmful responses.

Large language models (LLMs) have demonstrated strong persuasive capabilities comparable to those of humans, offering promising benefits while raising societal concerns about their deployment. However, systematically evaluating the persuasive capabilities of LLMs is inherently challenging, as the effectiveness of persuasion among humans varies significantly across different domains. In this paper, we take a theory-driven approach to provide a scalable and principled framework for measuring the persuasive capabilities of LLMs. Grounded in the Bayesian Persuasion (BP) framework, we repurpose existing human-human persuasion datasets to construct environments for evaluating and training LLMs in strategic persuasion. Our results reveal that frontier models can consistently achieve high persuasion gains and exhibit sophisticated persuasion strategies that align with theoretical predictions. Building on this, we use reinforcement learning to train LLMs for strategic persuasion in our environments. Our results also demonstrate that even small LLMs can obtain significantly higher persuasion gains through reinforcement learning.

Conformal Prediction (CP) is a widely used technique for quantifying uncertainty in machine learning models. In its standard form, CP offers probabilistic guarantees on the coverage of the true label, but it is agnostic to sensitive attributes in the dataset. Several recent works have sought to incorporate fairness into CP by ensuring conditional coverage guarantees across different subgroups. One such method is Conformal Fairness (CF). In this work, we extend the CF framework to the Federated Learning setting and discuss how we can audit a federated model for fairness by analyzing the fairness-related gaps for different demographic groups. Ensuring model fairness is a critical thrust of trustworthy machine learning (ML). ML models, when not calibrated for fairness, are prone to developing biases at each stage of an ML pipeline, as reflected by their predictions Mehrabi et al. (2021). We define bias as disparate performance (i.e., accuracy for classification) between different sub-populations. In the data collection phase, measurement bias may occur due to disproportionate data collection on sub-populations, while representation bias manifests from a lack of training data on specific strata. During training, these biases are inductively learned by the model-leading to incorrect predictions in safety-critical tasks. These models are also susceptible to algorithmic bias, resulting from regularization and optimization techniques during model training, which incorrectly generalize for marginal-ized groups. To mitigate these risks, many ML models must adhere to regulations placed by local governing bodies (Hirsch et al., 2023). Towards model compliance, Komala et al. (2024); Agrawal et al. (2024); Jones et al. (2025) have proposed approaches to enhance model fairness in varying tasks, including federated graph learning and representation learning.

This paper presents Extract-0, a 7-billion parameter language model specifically optimized for document information extraction that achieves performance exceeding models with parameter counts several orders of magnitude larger. Through a novel combination of synthetic data generation, supervised fine-tuning with Low-Rank Adaptation (LoRA), and reinforcement learning via Group Relative Policy Optimization (GRPO), Extract-0 achieves a mean reward of 0.573 on a benchmark of 1,000 diverse document extraction tasks, outperforming GPT-4.1 (0.457), o3 (0.464), and GPT-4.1-2025 (0.459). The training methodology employs a memory-preserving synthetic data generation pipeline that produces 280,128 training examples from diverse document sources, followed by parameterefficient fine-tuning that modifies only 0.53% of model weights (40.4M out of 7.66B parameters). The reinforcement learning phase introduces a novel semantic similarity-based reward function that handles the inherent ambiguity in information extraction tasks. This research demonstrates that task-specific optimization can yield models that surpass general-purpose systems while requiring substantially fewer computational resource.

As increasingly capable large language model (LLM)-based agents are developed, the potential harms caused by misalignment and loss of control grow correspondingly severe. To address these risks, we propose an approach that directly measures and controls the agency of these AI systems. We conceptualize the agency of LLM-based agents as a property independent of intelligence-related measures and consistent with the interdisciplinary literature on the concept of agency. We offer (1) agency as a system property operationalized along the dimensions of preference rigidity, independent operation, and goal persistence, (2) a representation engineering approach to the measurement and control of the agency of an LLM-based agent, and (3) regulatory tools enabled by this approach: mandated testing protocols, domain-specific agency limits, insurance frameworks that price risk based on agency, and agency ceilings to prevent societal-scale risks. We view our approach as a step toward reducing the risks that motivate the ``Scientist AI'' paradigm, while still capturing some of the benefits from limited agentic behavior.

Cloud computing is an established technology allowing users to share resources on a large scale, never before seen in IT history. A cloud system connects multiple individual servers in order to process related tasks in several environments at the same time. Clouds are typically more cost-effective than single computers of comparable computing performance. The sheer physical size of the system itself means that thousands of machines may be involved. The focus of this research was to design a strategy to dynamically allocate tasks without overloading Cloud nodes which would result in system stability being maintained at minimum cost. This research has added the following new contributions to the state of knowledge: (i) a novel taxonomy and categorisation of three classes of schedulers, namely OS-level, Cluster and Big Data, which highlight their unique evolution and underline their different objectives; (ii) an abstract model of cloud resources utilisation is specified, including multiple types of resources and consideration of task migration costs; (iii) a virtual machine live migration was experimented with in order to create a formula which estimates the network traffic generated by this process; (iv) a high-fidelity Cloud workload simulator, based on a month-long workload traces from Google's computing cells, was created; (v) two possible approaches to resource management were proposed and examined in the practical part of the manuscript: the centralised metaheuristic load balancer and the decentralised agent-based system. The project involved extensive experiments run on the University of Westminster HPC cluster, and the promising results are presented together with detailed discussions and a conclusion.

Large Language Models (LLMs) are increasingly deployed across diverse domains but often exhibit disparities in how they handle real-life queries. To systematically investigate these effects within various disability contexts, we introduce \textbf{AccessEval (Accessibility Evaluation)}, a benchmark evaluating 21 closed- and open-source LLMs across 6 real-world domains and 9 disability types using paired Neutral and Disability-Aware Queries. We evaluated model outputs with metrics for sentiment, social perception, and factual accuracy. Our analysis reveals that responses to disability-aware queries tend to have a more negative tone, increased stereotyping, and higher factual error compared to neutral queries. These effects show notable variation by domain and disability type, with disabilities affecting hearing, speech, and mobility disproportionately impacted. These disparities reflect persistent forms of ableism embedded in model behavior. By examining model performance in real-world decision-making contexts, we better illuminate how such biases can translate into tangible harms for disabled users. This framing helps bridges the gap between technical evaluation and user impact, reinforcing importance of bias mitigation in day-to-day applications. Our dataset is publicly available at: https://huggingface.co/datasets/Srikant86/AccessEval

Open digital public infrastructure needs community management to ensure accountability, sustainability, and robustness. Yet open-source projects often rely on centralized decision-making, and the determinants of successful community management remain unclear. We analyze 637 GitHub repositories to trace transitions from founder-led to shared governance. Specifically, we document trajectories to community governance by extracting institutional roles, actions, and deontic cues from version-controlled project constitutions (GOVERNANCE.md). With a semantic parsing pipeline, we cluster elements into broader role and action types. We find roles and actions grow, and regulation becomes more balanced, reflecting increases in governance scope and differentiation over time. Rather than shifting tone, communities grow by layering and refining responsibilities. As transitions to community management mature, projects increasingly regulate ecosystem-level relationships and add definition to project oversight roles. Overall, this work offers a scalable pipeline for tracking the growth and development of community governance regimes from open-source software's familiar default of founder-ownership.