@misc{13730,
  abstract     = {{This paper introduces an LLM-mediated AI Advisor that contextualizes and synthesizes heterogeneous explainable AI (XAI) outputs to support fast and calibrated misinformation judgments in time-sensitive social media settings. We define LLM-mediated XAI as a process in which a large language model aggregates, prioritizes, and translates heterogeneous XAI outputs into a context-sensitive explanation tailored to the user’s decision situation. Semantic features, XAI modules and LLM-based summarization and synthesis enable the generation of explanations that are adapted in three ways: compressed for time-efficient decisions, translated into non-technical language, and progressively expandable for deeper inspection. Through a mixed-methods user study, including a quantitative study and a qualitative study, we analyze how users interpret, challenge and strategically rely on LLM-mediated explanations during real-world misinformation assessment tasks. The findings indicate that the approach reduces time-to-decision and supports critical inspection without inducing over-reliance. Progressive disclosure and different techniques to present information favored different user needs while conversational functionality was rarely used due to unclear benefits and fear of confusion.}},
  author       = {{Grimm, Valentin and Rubart, Jessica and Herder, Eelco and Röcker, Carsten}},
  booktitle    = {{WebSci Companion '26: Companion Publication of the 2026 18th ACM Web Science Conference}},
  editor       = {{Balke, Wolf-Tilo and Plötzky, Florian and Spaniol, Marc and Herder, Eelco and Manikonda, Lydia and Liu, Haiming and Ibáñez, Luis-Daniel and Rezapour, Rezvaneh}},
  isbn         = {{979-8-4007-2492-3}},
  keywords     = {{Large Language Model Mediation, Explainable AI, Decision Co- Pilot Systems, Misinformation Detection}},
  location     = {{Braunschweig}},
  pages        = {{110--116}},
  publisher    = {{ACM}},
  title        = {{{LLM-Mediated XAI Explanations: An AI Advisor for Fast and Calibrated Judgments on Potential Misinformation}}},
  doi          = {{https://doi.org/10.1145/3795513.3810452}},
  year         = {{2026}},
}

@misc{11283,
  abstract     = {{Introduction: In recent decades, there has been a rise in mental illnesses. Community infrastructures are increasingly acknowledged as important for sustaining good mental health. Moreover, green spaces are anticipated to offer advantages for both mental health and social cohesion. However, the mediating pathway between green space, social cohesion and mental health and especially the proximity and characteristics of green spaces that trigger these potential effects remain of interest. Methods: We gathered data from 1365 individuals on self-reported social cohesion and mental health across four satellite districts in European cities: Nantes (France), Porto (Portugal), Sofia (Bulgaria), and Hoje-Taastrup (Denmark). Green space data from OpenStreetMap was manually adjusted using the PRIGSHARE guidelines. We used the AID-PRIGSHARE tool to generate 7 indicators about green space characteristics measured in distances from 100-1500 m, every 100 m. This resulted in 105 different green space variables that we tested in a single mediation model with structural equation modelling. Results: Accessible greenness (900-1400 m), accessible green spaces (900-1500 m), accessible green space corridors (300-800 m), accessible total green space (300-800), and mix of green space uses (700-1100 m) were significantly associated with social cohesion and indirectly with mental health. Green corridors also showed negative indirect and direct associations with mental health in larger distances. Surrounding greenness and the quantity of green space uses were not associated with social cohesion nor indirectly with mental health. We also observed no positive direct associations between any green space variable in any distance to mental health. Conclusions: Our results suggest that accessibility, connectivity, mix of use and proximity are key characteristics that drive the relationship between green spaces, social cohesion and mental health. This gives further guidance to urban planners and decision-makers on how to design urban green spaces to foster social cohesion and improve mental health.}},
  author       = {{Cardinali, Marcel and Beenackers, Mariëlle A. and Fleury-Bahi, Ghozlane and Bodénan, Philippe and Petrova, Milena Tasheva and van Timmeren, Arjan and Pottgiesser, Uta}},
  booktitle    = {{  Urban forestry & urban greening}},
  issn         = {{1610-8167}},
  keywords     = {{Soil Science, Ecology, Forestry, Green space, Mediation, Social cohesion, Well-being, Structural equation modelling}},
  publisher    = {{Elsevier BV}},
  title        = {{{Examining green space characteristics for social cohesion and mental health outcomes: A sensitivity analysis in four European cities}}},
  doi          = {{10.1016/j.ufug.2024.128230}},
  volume       = {{93}},
  year         = {{2024}},
}

@misc{13797,
  abstract     = {{The research objective was to examine if the significant findings between green space, social cohesion and mental health stem from unique green space characteristics or similar mechanisms. This dataset is a correlation matrix of 105 green space indicators gathered in GIS, covering 7 different green space characteristics (surrounding greenness (NDVI 0-1), accessible greenness (NDVI 0-1), accessible green space (m2), accessible green corridors (m2), accessible total green space (m2), sum of green space uses (n), mix of green space uses(n)) in 15 distances from 100 to 1,500 m every 100 m.}},
  author       = {{Cardinali, Marcel}},
  keywords     = {{Green Space, Mediation, social cohesion, structural equation modelling, well-being}},
  publisher    = {{TU Delft}},
  title        = {{{Data underlying the publication: Examining green space characteristics for social cohesion and mental health outcomes: A sensitivity analysis in four European cities}}},
  doi          = {{10.4121/9E6581A4-D5CE-4B94-8642-4774051A2FD8.V1}},
  year         = {{2024}},
}

@misc{13609,
  abstract     = {{Evaluative conditioning (EC) refers to changes in the evaluation of a conditioned stimulus (CS) due to its repeated pairing with an unconditioned stimulus (US). One of the most debated topics in EC research is whether or not EC is dependent on contingency awareness. In this study, we go beyond this debate by examining whether contingency awareness mediates the impact of attentional resources and goal-directed attention on EC. Attentional resources were manipulated by presenting CSs and USs either within the same modality or in different modalities. Goal-directed attention was manipulated by asking participants to respond to the CSs or to the USs. Results indicate that the effect of goal-directed attention on EC is mediated by contingency awareness, whereas the effect of attentional resources on EC is not.}},
  author       = {{Blask, Katharina and Walther, Eva and Halbeisen, Georg and Weil, Rebecca}},
  booktitle    = {{Learning and Motivation}},
  issn         = {{1095-9122}},
  keywords     = {{Evaluative conditioning, Contingency awareness, Attentional resources, Goal-directed attention, Mediation}},
  number       = {{3}},
  pages        = {{99--106}},
  publisher    = {{Academic Press}},
  title        = {{{At the crossroads: Attention, contingency awareness, and evaluative conditioning}}},
  doi          = {{10.1016/j.lmot.2012.03.004}},
  volume       = {{43}},
  year         = {{2012}},
}