@article{61221,
  author       = {{Jimenez, Patricia}},
  journal      = {{Ethnography & Education}},
  title        = {{{The Accomplishment of Rights, Obligations and other Expectation: Attending to the Lived Details of Classroom Order to Consider the Ethnographic Grasp of ‘Elusive Emotions’}}},
  year         = {{2026}},
}

@inbook{61220,
  abstract     = {{This chapter presents recurring structures of interactions—and their associated goals—as they occur in explaining processes. It explores how explanations are not delivered in isolation but unfold through dynamic, structured sequences of interaction between participants. Beginning with the smallest units, we examine how individual dialog acts and multimodal signals form micro-patterns within turns. These, in turn, compose meso-level structures such as pragmatic frames, that organize sequences of interaction into meaningful, goal-oriented episodes. At the macro-level, we identify common types of explanatory dialogues, such as inquiry, information-seeking, or deliberation, which are shaped by participants’ goals and situational demands. The chapter highlights how these abstract patterns of structure are instantiated differently across social and situational contexts and proposes that understanding them is crucial for designing socially intelligent and adaptive XAI systems. By analyzing how these structures emerge and function, we o!er a framework for operationalizing explanation structures in a way that supports co-constructive and context-sensitive human-AI interaction.}},
  author       = {{Jimenez, Patricia and Vollmer, Anna Lisa and Wachsmuth, Henning }},
  booktitle    = {{Social Explainable AI: Communications of NII Shonan Meetings}},
  editor       = {{Rohlfing, Katharina and Främling, Kary and Lim, Brian and Alpsancar, Suzana and Thommes, Kirsten}},
  publisher    = {{Springer Singapore}},
  title        = {{{Structures Underlying Explanations}}},
  year         = {{2026}},
}

@inproceedings{61234,
  abstract     = {{The ability to generate explanations that are understood by explainees is the
quintessence of explainable artificial intelligence. Since understanding
depends on the explainee's background and needs, recent research focused on
co-constructive explanation dialogues, where an explainer continuously monitors
the explainee's understanding and adapts their explanations dynamically. We
investigate the ability of large language models (LLMs) to engage as explainers
in co-constructive explanation dialogues. In particular, we present a user
study in which explainees interact with an LLM in two settings, one of which
involves the LLM being instructed to explain a topic co-constructively. We
evaluate the explainees' understanding before and after the dialogue, as well
as their perception of the LLMs' co-constructive behavior. Our results suggest
that LLMs show some co-constructive behaviors, such as asking verification
questions, that foster the explainees' engagement and can improve understanding
of a topic. However, their ability to effectively monitor the current
understanding and scaffold the explanations accordingly remains limited.}},
  author       = {{Fichtel, Leandra and Spliethöver, Maximilian and Hüllermeier, Eyke and Jimenez, Patricia and Klowait, Nils and Kopp, Stefan and Ngonga Ngomo, Axel-Cyrille and Robrecht, Amelie and Scharlau, Ingrid and Terfloth, Lutz and Vollmer, Anna-Lisa and Wachsmuth, Henning}},
  booktitle    = {{Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue}},
  publisher    = {{Association for Computational Linguistics}},
  title        = {{{Investigating Co-Constructive Behavior of Large Language Models in  Explanation Dialogues}}},
  year         = {{2025}},
}

@unpublished{60718,
  abstract     = {{The ability to generate explanations that are understood by explainees is the
quintessence of explainable artificial intelligence. Since understanding
depends on the explainee's background and needs, recent research focused on
co-constructive explanation dialogues, where an explainer continuously monitors
the explainee's understanding and adapts their explanations dynamically. We
investigate the ability of large language models (LLMs) to engage as explainers
in co-constructive explanation dialogues. In particular, we present a user
study in which explainees interact with an LLM in two settings, one of which
involves the LLM being instructed to explain a topic co-constructively. We
evaluate the explainees' understanding before and after the dialogue, as well
as their perception of the LLMs' co-constructive behavior. Our results suggest
that LLMs show some co-constructive behaviors, such as asking verification
questions, that foster the explainees' engagement and can improve understanding
of a topic. However, their ability to effectively monitor the current
understanding and scaffold the explanations accordingly remains limited.}},
  author       = {{Fichtel, Leandra and Spliethöver, Maximilian and Hüllermeier, Eyke and Jimenez, Patricia and Klowait, Nils and Kopp, Stefan and Ngonga Ngomo, Axel-Cyrille and Robrecht, Amelie and Scharlau, Ingrid and Terfloth, Lutz and Vollmer, Anna-Lisa and Wachsmuth, Henning}},
  booktitle    = {{arXiv:2504.18483}},
  pages        = {{20}},
  title        = {{{Investigating Co-Constructive Behavior of Large Language Models in  Explanation Dialogues}}},
  year         = {{2025}},
}