We utilize a within-subjects design with randomized task assignments to understand the effectiveness of using an AI retrieval augmented generation (RAG) tool to assist analysts with an information extraction and data annotation task. We replicate an existing, challenging real-world annotation task with complex multi-part criteria on a set of thousands of pages of public disclosure documents from global systemically important banks (GSIBs) with heterogeneous and incomplete information content. We test two treatment conditions. First, a "naive" AI use condition in which annotators use only the tool and must accept the first answer they are given. And second, an "interactive" AI treatment condition where annotators use the tool interactively, and use their judgement to follow-up with additional information if necessary. Compared to the human-only baseline, the use of the AI tool accelerated task execution by up to a factor of 10 and enhanced task accuracy, particularly in the interactive condition. We find that when extrapolated to the full task, these methods could save up to 268 hours compared to the human-only approach. Additionally, our findings suggest that annotator skill, not just with the subject matter domain, but also with AI tools, is a factor in both the accuracy and speed of task performance.

Despite the rapid expansion of electric vehicle (EV) charging networks, questions remain about their efficiency in meeting the growing needs of EV drivers. Previous simulation-based approaches, which rely on static behavioural rules, have struggled to capture the adaptive behaviours of human drivers. Although reinforcement learning has been introduced in EV simulation studies, its application has primarily focused on optimising fleet operations rather than modelling private drivers who make independent charging decisions. Additionally, long-distance travel remains a primary concern for EV drivers. However, existing simulation studies rarely explore charging behaviour over large geographical scales. To address these gaps, we propose a multi-stage reinforcement learning framework that simulates EV charging demand across large geographical areas. We validate the model against real-world data, and identify the training stage that most closely reflects actual driver behaviour, which captures both the adaptive behaviours and bounded rationality of private drivers. Based on the simulation results, we also identify critical 'charging deserts' where EV drivers consistently have low state of charge. Our findings also highlight recent policy shifts toward expanding rapid charging hubs along motorway corridors and city boundaries to meet the demand from long-distance trips.

Accurately predicting the outcome of a trial of labor after cesarean (TOLAC) is essential for guiding prenatal counseling and minimizing delivery-related risks. This study presents supervised machine learning models for predicting vaginal birth after cesarean (VBAC) using 643,029 TOLAC cases from the CDC WONDER Natality dataset (2017-2023). After filtering for singleton births with one or two prior cesareans and complete data across 47 prenatal-period features, three classifiers were trained: logistic regression, XGBoost, and a multilayer perceptron (MLP). The MLP achieved the highest performance with an AUC of 0.7287, followed closely by XGBoost (AUC = 0.727), both surpassing the logistic regression baseline (AUC = 0.709). To address class imbalance, class weighting was applied to the MLP, and a custom loss function was implemented in XGBoost. Evaluation metrics included ROC curves, confusion matrices, and precision-recall analysis. Logistic regression coefficients highlighted maternal BMI, education, parity, comorbidities, and prenatal care indicators as key predictors. Overall, the results demonstrate that routinely collected, early-pregnancy variables can support scalable and moderately high-performing VBAC prediction models. These models offer potential utility in clinical decision support, particularly in settings lacking access to specialized intrapartum data.

AI-driven clinical text classification is vital for explainable automated retrieval of population-level health information. This work investigates whether human-based clinical rationales can serve as additional supervision to improve both performance and explainability of transformer-based models that automatically encode clinical documents. We analyzed 99,125 human-based clinical rationales that provide plausible explanations for primary cancer site diagnoses, using them as additional training samples alongside 128,649 electronic pathology reports to evaluate transformer-based models for extracting primary cancer sites. We also investigated sufficiency as a way to measure rationale quality for pre-selecting rationales. Our results showed that clinical rationales as additional training data can improve model performance in high-resource scenarios but produce inconsistent behavior when resources are limited. Using sufficiency as an automatic metric to preselect rationales also leads to inconsistent results. Importantly, models trained on rationales were consistently outperformed by models trained on additional reports instead. This suggests that clinical rationales don't consistently improve model performance and are outperformed by simply using more reports. Therefore, if the goal is optimizing accuracy, annotation efforts should focus on labeling more reports rather than creating rationales. However, if explainability is the priority, training models on rationale-supplemented data may help them better identify rationale-like features. We conclude that using clinical rationales as additional training data results in smaller performance improvements and only slightly better explainability (measured as average token-level rationale coverage) compared to training on additional reports.

The emergence of AI agents powered by large language models (LLMs) marks a pivotal shift toward the Agentic Web, a new phase of the internet defined by autonomous, goal-driven interactions. In this paradigm, agents interact directly with one another to plan, coordinate, and execute complex tasks on behalf of users. This transition from human-driven to machine-to-machine interaction allows intent to be delegated, relieving users from routine digital operations and enabling a more interactive, automated web experience. In this paper, we present a structured framework for understanding and building the Agentic Web. We trace its evolution from the PC and Mobile Web eras and identify the core technological foundations that support this shift. Central to our framework is a conceptual model consisting of three key dimensions: intelligence, interaction, and economics. These dimensions collectively enable the capabilities of AI agents, such as retrieval, recommendation, planning, and collaboration. We analyze the architectural and infrastructural challenges involved in creating scalable agentic systems, including communication protocols, orchestration strategies, and emerging paradigms such as the Agent Attention Economy. We conclude by discussing the potential applications, societal risks, and governance issues posed by agentic systems, and outline research directions for developing open, secure, and intelligent ecosystems shaped by both human intent and autonomous agent behavior. A continuously updated collection of relevant studies for agentic web is available at: https://github.com/SafeRL-Lab/agentic-web.

Transformers have profoundly influenced AI research, but explaining their decisions remains challenging -- even for relatively simpler tasks such as classification -- which hinders trust and safe deployment in real-world applications. Although activation-based attribution methods effectively explain transformer-based text classification models, our findings reveal that these methods can be undermined by class-irrelevant features within activations, leading to less reliable interpretations. To address this limitation, we propose Contrast-CAT, a novel activation contrast-based attribution method that refines token-level attributions by filtering out class-irrelevant features. By contrasting the activations of an input sequence with reference activations, Contrast-CAT generates clearer and more faithful attribution maps. Experimental results across various datasets and models confirm that Contrast-CAT consistently outperforms state-of-the-art methods. Notably, under the MoRF setting, it achieves average improvements of x1.30 in AOPC and x2.25 in LOdds over the most competing methods, demonstrating its effectiveness in enhancing interpretability for transformer-based text classification.

This short paper is a primer on the nature of state sovereignty and the importance of claims about it. It also aims to reveal (merely reveal) a strategy for working with vague or contradictory data about which states, in fact, are sovereign. These goals together are intended to set the stage for applied work in ontology about international affairs.

Effectively leveraging diversity has been shown to improve performance for various machine learning models, including large language models (LLMs). However, determining the most effective way of using diversity remains a challenge. In this work, we compare two diversity approaches for answering binary questions using LLMs: model diversity, which relies on multiple models answering the same question, and question interpretation diversity, which relies on using the same model to answer the same question framed in different ways. For both cases, we apply majority voting as the ensemble consensus heuristic to determine the final answer. Our experiments on boolq, strategyqa, and pubmedqa show that question interpretation diversity consistently leads to better ensemble accuracy compared to model diversity. Furthermore, our analysis of GPT and LLaMa shows that model diversity typically produces results between the best and the worst ensemble members without clear improvement.

As large language models (LLMs) are increasingly deployed in high-risk domains such as law, finance, and medicine, systematically evaluating their domain-specific safety and compliance becomes critical. While prior work has largely focused on improving LLM performance in these domains, it has often neglected the evaluation of domain-specific safety risks. To bridge this gap, we first define domain-specific safety principles for LLMs based on the AMA Principles of Medical Ethics, the ABA Model Rules of Professional Conduct, and the CFA Institute Code of Ethics. Building on this foundation, we introduce Trident-Bench, a benchmark specifically targeting LLM safety in the legal, financial, and medical domains. We evaluated 19 general-purpose and domain-specialized models on Trident-Bench and show that it effectively reveals key safety gaps -- strong generalist models (e.g., GPT, Gemini) can meet basic expectations, whereas domain-specialized models often struggle with subtle ethical nuances. This highlights an urgent need for finer-grained domain-specific safety improvements. By introducing Trident-Bench, our work provides one of the first systematic resources for studying LLM safety in law and finance, and lays the groundwork for future research aimed at reducing the safety risks of deploying LLMs in professionally regulated fields. Code and benchmark will be released at: https://github.com/zackhuiiiii/TRIDENT

Large Language Models (LLMs) demonstrate complex responses to threat-based manipulations, revealing both vulnerabilities and unexpected performance enhancement opportunities. This study presents a comprehensive analysis of 3,390 experimental responses from three major LLMs (Claude, GPT-4, Gemini) across 10 task domains under 6 threat conditions. We introduce a novel threat taxonomy and multi-metric evaluation framework to quantify both negative manipulation effects and positive performance improvements. Results reveal systematic vulnerabilities, with policy evaluation showing the highest metric significance rates under role-based threats, alongside substantial performance enhancements in numerous cases with effect sizes up to +1336%. Statistical analysis indicates systematic certainty manipulation (pFDR < 0.0001) and significant improvements in analytical depth and response quality. These findings have dual implications for AI safety and practical prompt engineering in high-stakes applications.