Dreading negative outcomes is six times more powerful than anticipating the positive ones. Breakthroughs, discoveries, and DIY tips sent six days a week. Dread shapes our decision making and new research published in the journal explores why spinning those negative scenarios affects us more than the possible positive outcomes. The team from the University of Bath in England and the University of Waterloo in Canada analyzed data from the British Household Panel Survey (BHPS). The team looked at roughly 14,000 individuals between 1991 and 2024, tracking emotional responses to real-world economic choices including investing, changing jobs, or making health decisions.

Explanations such as these that employ "even if..." reasoning,

We train our models with the ADAM optimizer using a learning rate of 0.002. A.2 Data Processing We use the following features for training our models. Our approach allows for customization of actionable features and constraints on their values. We require that education level can only increase. The actionable features are: (i) education level and (ii) the number of prison rule violations reported during the sample sentence.

Explanations are important not only to ensure that there are no issues with the way the prediction is made (e.g., making sure the decision is free of

Large Language Models (LLMs) are increasingly deployed in autonomous decision-making roles across high-stakes domains. However, since models are trained on human-generated data, they may inherit cognitive biases that systematically distort human judgment, including escalation of commitment, where decision-makers continue investing in failing courses of action due to prior investment. Understanding when LLMs exhibit such biases presents a unique challenge. While these biases are well-documented in humans, it remains unclear whether they manifest consistently in LLMs or require specific triggering conditions. This paper investigates this question using a two-stage investment task across four experimental conditions: model as investor, model as advisor, multi-agent deliberation, and compound pressure scenario. Across N = 6,500 trials, we find that bias manifestation in LLMs is highly context-dependent. In individual decision-making contexts (Studies 1-2, N = 4,000), LLMs demonstrate strong rational cost-benefit logic with minimal escalation of commitment. However, multi-agent deliberation reveals a striking hierarchy effect (Study 3, N = 500): while asymmetrical hierarchies show moderate escalation rates (46.2%), symmetrical peer-based decision-making produces near-universal escalation (99.2%). Similarly, when subjected to compound organizational and personal pressures (Study 4, N = 2,000), models exhibit high degrees of escalation of commitment (68.95% average allocation to failing divisions). These findings reveal that LLM bias manifestation depends critically on social and organizational context rather than being inherent, with significant implications for the deployment of multi-agent systems and unsupervised operations where such conditions may emerge naturally.

Would you trust an artificial intelligence software to make a diagnosis for you? Most people would answer negatively to this question. Indeed, despite the significant advancements of AI and neural networks, their "black box" nature is a significant barrier to our trust. The inability to understand how or why a model arrives at its conclusions leaves many skeptical about its use, particularly in sensitive areas like healthcare, finance, or legal systems. This is where Explainable AI (XAI) comes into play, a research area focused on interpreting AI models' predictions.

We introduce a fairness-aware dataset for job recommendation in advertising, designed to foster research in algorithmic fairness within real-world scenarios. It was collected and prepared to comply with privacy standards and business confidentiality. An additional challenge is the lack of access to protected user attributes such as gender, for which we propose a solution to obtain a proxy estimate. Despite being anonymized and including a proxy for a sensitive attribute, our dataset preserves predictive power and maintains a realistic and challenging benchmark. This dataset addresses a significant gap in the availability of fairness-focused resources for high-impact domains like advertising -- the actual impact being having access or not to precious employment opportunities, where balancing fairness and utility is a common industrial challenge. We also explore various stages in the advertising process where unfairness can occur and introduce a method to compute a fair utility metric for the job recommendations in online systems case from a biased dataset. Experimental evaluations of bias mitigation techniques on the released dataset demonstrate potential improvements in fairness and the associated trade-offs with utility.