We evaluate how well large language model embeddings represent continuous numerical values across different precisions and ranges. Using linear models and principal component analysis on models from major providers, we show that while embeddings can reconstruct numbers with high fidelity (R2 ≥ 0.95), they introduce substantial noise, with principal components explaining less than 40% of embedding variance. Performance degrades with increasing decimal precision and mixed-sign values, revealing fundamental limitations in how these models encode numerical information.

The principal benefit of unsupervised representation learning is that a pre-trained model can be fine-tuned where data or labels are scarce. Existing approaches for graph representation learning are domain specific, maintaining consistent node and edge features across the pre-training and target datasets. This has precluded transfer to multiple domains. We present Topology Only Pre-Training (ToP), a graph pre-training method based on node and edge feature exclusion. We show positive transfer on evaluation datasets from multiple domains, including domains not present in pre-training data, running directly contrary to assumptions made in contemporary works. On 75% of experiments, ToP models perform significantly ([Formula: see text]) better than a supervised baseline. Performance is significantly positive on 85.7% of tasks when node and edge features are used in fine-tuning. We further show that out-of-domain topologies can produce more useful pre-training than in-domain. Under ToP we show better transfer from non-molecule pre-training, compared to molecule pre-training, on 79% of molecular benchmarks. Against the limited set of other generalist graph models ToP performs strongly, including against models with many orders of magnitude larger. These findings show that ToP opens broad areas of research in both transfer learning on scarcely populated graph domains and in graph foundation models. Supplementary Information: The online version contains supplementary material available at 10.1007/s10618-026-01210-1.

Social norms are standards of behaviour common in a society. However, when agents make decisions without considering how others are impacted, norms can emerge that lead to the subjugation of certain agents. We present RAWL·E, a method to create ethical norm-learning agents. RAWL·E agents operationalise maximin, a fairness principle from Rawlsian ethics, in their decision-making processes to promote ethical norms by balancing societal well-being with individual goals. We evaluate RAWL·E agents in simulated harvesting scenarios. We find that norms emerging in RAWL·E agent societies enhance social welfare, fairness, and robustness, and yield higher minimum experience compared to those that emerge in agent societies that do not implement Rawlsian ethics.

We propose Exanna, a framework to realize agents that incorporate values in decision making. An Exanna agent considers the values of itself and others when providing rationales for its actions and evaluating the rationales provided by others. Via multiagent simulation, we demonstrate that considering values in decision making and producing rationales, especially for norm-deviating actions, leads to (1) higher conflict resolution, (2) better social experience, (3) higher privacy, and (4) higher flexibility.

Artificial intelligence raises important social and ethical concerns, especially about accountability, autonomy, dignity, and justice. We focus on the specific concerns arising from how the emerging autonomous vehicle (AV) technology will affect professional drivers. We posit that we must engage with stakeholders to understand the implications of a technology that will affect the stakeholders’ lives, livelihoods, or wellbeing. We conducted nine in-depth interviews with professional drivers, with at least two years of driving experience, to understand the ethical and societal challenges from the drivers’ perspective during the predicted widespread implementation of AVs. Safety was the most commonly discussed issue, which was mentioned by all drivers (17 times by truck drivers and 18 times by Uber/Lyft drivers). We find that although drivers agree that AVs will significantly impact future transportation systems, they are apprehensive about the prospects of reskilling for other jobs and want their employers to be straightforward in how the introduction of AVs will affect them. Additionally, drivers dismiss the suggestions that driving jobs are unsatisfying and potentially unhealthy and thus should be eliminated. These findings should be considered seriously in decision-making about questions of socioeconomic justice, and could be useful to policymakers as they shape relevant regulations.

Norms help regulate a society. Norms may be explicit (represented in structured form) or implicit. We address the emergence of explicit norms by developing agents who provide and reason about explanations for norm violations in deciding sanctions and identifying alternative norms. These agents use a genetic algorithm to produce norms and reinforcement learning to learn the values of these norms. We find that applying explanations leads to norms that provide better cohesion and goal satisfaction for the agents. Our results are stable for societies with differing attitudes of generosity.

Multi-agent systems provide a basis for developing systems of autonomous entities and thus find application in a variety of domains. We consider a setting where not only the member agents are adaptive but also the multi-agent system viewed as an entity in its own right is adaptive. Specifically, the social structure of a multi-agent system can be reflected in the social norms among its members. It is well recognized that the norms that arise in society are not always beneficial to its members. We focus on prosocial norms, which help achieve positive outcomes for society and often provide guidance to agents to act in a manner that takes into account the welfare of others. Specifically, we propose Cha, a framework for the emergence of prosocial norms. Unlike previous norm emergence approaches, Cha supports continual change to a system (agents may enter and leave) and dynamism (norms may change when the environment changes). Importantly, Cha agents incorporate prosocial decision-making based on inequity aversion theory, reflecting an intuition of guilt arising from being antisocial. In this manner, Cha brings together two important themes in prosociality: decision-making by individuals and fairness of system-level outcomes. We demonstrate via simulation that Cha can improve aggregate societal gains and fairness of outcomes.

We address the problem of engineering a sociotechnical system (STS) with respect to its stakeholders’ requirements. We motivate a two-tier STS conception composed of a technical tier that provides control mechanisms and describes what actions are allowed by the software components, and a social tier that characterizes the stakeholders’ expectations of each other in terms of norms. We adopt agents as computational entities, each representing a different stakeholder. Unlike previous approaches, our framework, D ESEN , incorporates the social dimension into the formal verification process. Thus, D ESEN supports agents potentially violating applicable norms—a consequence of their autonomy. In addition to requirements verification, D ESEN supports refinement of STS specifications via design patterns to meet stated requirements. We evaluate D ESEN at three levels. We illustrate how D ESEN carries out refinement via the application of patterns on a hospital emergency scenario. We show via a human-subject study that a design process based on our patterns is helpful for participants who are inexperienced in conceptual modeling and norms. We provide an agent-based environment to simulate the hospital emergency scenario to compare STS specifications (including participant solutions from the human-subject study) with metrics indicating social welfare and norm compliance, and other domain dependent metrics.

We study how emotions influence norm outcomes in decision-making contexts. Following the literature, we provide baseline Dynamic Bayesian models to capture an agent's two perspectives on a directed norm. Unlike the literature, these models are holistic in that they incorporate not only norm outcomes and emotions but also trust and goals. We obtain data from an empirical study involving game play with respect to the above variables. We provide a step-wise process to discover two new Dynamic Bayesian models based on maximizing log-likelihood scores with respect to the data. We compare the new models with the baseline models to discover new insights into the relevant relationships. Our empirically supported models are thus holistic and characterize how emotions influence norm outcomes better than previous approaches.

Norms describe the social architecture of a society and govern the interactions of its member agents. It may be appropriate for an agent to deviate from a norm; the deviation being indicative of a specialized norm applying under a specific context. Existing approaches for norm emergence assume simplified interactions wherein deviations are negatively sanctioned. We investigate via simulation the benefits of enriched interactions where deviating agents share selected elements of their contexts. We find that as a result (1) the norms are learned better with fewer sanctions, indicating improved social cohesion; and (2) the agents are better able to satisfy their individual goals. These results are robust under societies of varying sizes and characteristics reflecting pragmatic, considerate, and selfish agents.

Automated app review analysis is an important avenue for extracting a variety of requirements-related information. Typically, a first step toward performing such analysis is preparing a training dataset, where developers (experts) identify a set of reviews and, manually, annotate them according to a given task. Having sufficiently large training data is important for both achieving a high prediction accuracy and avoiding overfitting. Given millions of reviews, preparing a training set is laborious. We propose to incorporate active learning, a machine learning paradigm, in order to reduce the human effort involved in app review analysis. Our app review classification framework exploits three active learning strategies based on uncertainty sampling. We apply these strategies to an existing dataset of 4,400 app reviews for classifying app reviews as features, bugs, rating, and user experience. We find that active learning, compared to a training dataset chosen randomly, yields a significantly higher prediction accuracy under multiple scenarios.

We propose Kont, a formal framework for comparing normative multiagent systems (nMASs) by computing tradeoffs among liveness (something good happens) and safety (nothing bad happens). Safety-focused nMASs restrict agents' actions to avoid undesired enactments. However, such restrictions hinder liveness, particularly in situations such as medical emergencies. We formalize tradeoffs using norms, and develop an approach for understanding to what extent an nMAS promotes liveness or safety. We propose patterns to guide the design of an nMAS with respect to liveness and safety, and prove their correctness. We further quantify liveness and safety using heuristic metrics for an emergency healthcare application. We show that the results of the application corroborate our theoretical development.

Privacy news influences end-user attitudes and behaviors as well as product and policy development, and so is an important data source for understanding privacy perceptions. We provide a largescale text mining of privacy news, focusing on patterns in sentiment and keywords. This is a challenging task given the lack of a privacy news repository and a ground truth for sentiment. Using high-precision data sets from two popular news sources in the U. S. and U. K., the New York Times and the Guardian, we find negative privacy news is far more common than positive. In addition, in the NYT, privacy news is more prominently reported than many world events involving significant human suffering. Our analysis provides a rich snapshot of this driver of privacy perceptions and demonstrates that news facilitates the systematization of privacy knowledge.

Crowd RE is an emerging avenue for engaging the general public or the so called crowd in variety of requirements engineering tasks. Crowd RE scales RE by involving, potentially, millions of users. Although humans are at the center of Crowd RE, automated techniques are necessary (1) to derive useful insights from large amounts of raw data the crowd can produce; and (2) to drive the Crowd RE process, itself, by facilitating novel workflows combining crowd and machine intelligence.To facilitate automated techniques for Crowd RE, first, we showcase a crowd-acquired dataset, consisting of requirements and their ratings on multiple dimensions for the smart homes application domain. Our dataset is unique in that it contains not only requirements, but also the characteristics of the crowd workers who produced those requirements including their demographics, personality traits, and creative potential. Understanding the crowd characteristics is essential to developing effective Crowd RE processes. Second, we outline key challenges involved in automating Crowd RE and describe, how our dataset can serve as a foundation for developing such automated techniques.

As a creative discipline, Requirements Engineering (RE), lends importance to understanding the associated human factors. Crowd RE, the approach of acquiring requirements from members of the public-the so-called crowd-emphasizes human factors further. We investigate how human personality and creative potential influence a requirement acquisition task. These factors are of specific importance to Crowd RE because (1) crowd workers are generally not trained in RE, and (2) a key motivation in engaging them is to benefit from their creativity. We propose a sequential Crowd RE process, where workers in one stage review requirements from the previous stage and produce additional requirements. To reduce potential information overload in this process, we propose strategies for selecting requirements from one stage to expose to workers in later stages. We conducted a study on Amazon Mechanical Turk tasking 300 workers with creating requirements via the above sequential process (in the domain of smart home applications for concreteness) and tasking an additional 300 workers to rate the creativity (novelty and usefulness) of those requirements. Our findings offer insights on how to carry out Crowd RE effectively. First, we find that a crowd worker's (1) creative potential, and personality traits of openness and conscientiousness have significant positive influence on the novelty of the worker's ideas, and (2) personality traits of agreeableness and conscientiousness have significant positive influence, but extraversion has significant negative influence on the usefulness of the worker's ideas. Second, we find that exposing a worker to ideas from previous workers cognitively stimulates the worker to produce creative ideas. Third, we identify effective strategies based on personality traits and creative potential for selecting a few requirements from a pool of previous requirements to stimulate a worker.

This paper reports on an ongoing interdisciplinary study of analytic workflow, describing our preliminary understanding and findings as well as some directions for further investigation and validation. Specifically, we exploit knowledge from organizational psychology to develop a computational organizational model. Our proposed organizational model provides a framework to understand the impact of organizational level variables and worker characteristics on workflow performance, providing a view to create justifiable interventions to improve performance. To evaluate the viability of the model, we develop a multiagent simulation framework and design an experimental study.