@inbook{61323, author = {{Wrede, Britta and Buschmeier, Hendrik and Rohlfing, Katharina Justine and Booshehri, Meisam and Grimminger, Angela}}, booktitle = {{Social Explainable AI}}, editor = {{Rohlfing, Katharina J. and Främling, Kary and Alpsancar, Suzana and Thommes, Kirsten and Lim, Brian Y.}}, pages = {{227--245}}, publisher = {{Springer}}, title = {{{Incremental communication}}}, doi = {{10.1007/978-981-96-5290-7_12}}, year = {{2026}}, } @inbook{61321, author = {{Grimminger, Angela and Buschmeier, Hendrik}}, booktitle = {{Social Explainable AI}}, editor = {{Rohlfing, Katharina J. and Främling, Kary and Alpsancar, Suzana and Thommes, Kirsten and Lim, Brian Y.}}, pages = {{351--365}}, publisher = {{Springer}}, title = {{{Theoretical aspects of multimodal processing}}}, doi = {{10.1007/978-981-96-5290-7_18}}, year = {{2026}}, } @inbook{61322, author = {{Lazarov, Stefan Teodorov and Tchappi, Igor and Grimminger, Angela}}, booktitle = {{Social Explainable AI}}, editor = {{Rohlfing, Katharina J. and Främling, Kary and Alpsancar, Suzana and Thommes, Kirsten and Lim, Brian Y.}}, pages = {{367--390}}, publisher = {{Springer}}, title = {{{Characteristics of nonverbal behavior}}}, doi = {{10.1007/978-981-96-5290-7_19}}, year = {{2026}}, } @inbook{61112, author = {{Rohlfing, Katharina J. and Vollmer, Anna-Lisa and Grimminger, Angela}}, booktitle = {{Social Explainable AI}}, editor = {{Rohlfing, Katharina and Främling, Kary and Thommes, Kirsten and Alpsancar, Suzana and Lim, Brian Y.}}, publisher = {{Springer}}, title = {{{Practices: How to establish an explaining practice}}}, doi = {{10.1007/978-981-96-5290-7_5}}, year = {{2026}}, } @inbook{65069, author = {{Främling, Kary and Alami, Rachid and Hulstijn, Joris and Tchappi, Igor and Grimminger, Angela and Wrede, Britta and Buschmeier, Hendrik and Kubler, Sylvain}}, booktitle = {{Social Explainable AI}}, editor = {{Rohlfing, Katharina J. and Främling, Kary and Alpsancar, Suzana and Thommes, Kirsten and Lim, Brian Y.}}, isbn = {{9789819652891}}, pages = {{19--38}}, publisher = {{Springer}}, title = {{{Scenarios of Social Explainable AI in practice}}}, doi = {{10.1007/978-981-96-5290-7_2}}, year = {{2026}}, } @inbook{61325, author = {{Vollmer, Anna-Lisa and Buhl, Heike M. and Alami, Rachid and Främling, Kary and Grimminger, Angela and Booshehri, Meisam and Ngonga Ngomo, Axel-Cyrille}}, booktitle = {{Social Explainable AI}}, editor = {{Rohlfing, Katharina J. and Främling, Kary and Lim, Brian and Alpsancar, Suzana and Thommes, Kirsten}}, pages = {{39--53}}, publisher = {{Springer}}, title = {{{Components of an explanation for co-constructive sXAI}}}, doi = {{10.1007/978-981-96-5290-7_3}}, year = {{2026}}, } @unpublished{61151, abstract = {{In this paper, we discuss the application of retrospective video recall for the assessment of cognitive processes in explanatory interactions, such as understanding and mental models. Our purpose is to reflect on the benefits and limitations of video recall compared to another self-report method, ‘thinking-aloud’. To do so, we reveal empirical results from the application of video recall in three interdisciplinary research projects that applied the method for the qualitative and quantitative assessment of cognitive and behavioral phenomena in everyday explanations. In all three projects, video recall was applied as a post-hoc procedure following the recording of dyadic face-to-face explanations of board games. The design of the video recall procedure differed between individual projects because they pursued different research objectives – that is the investigation of (1) an interlocutor's multimodal signals of understanding, (2) the change in assumptions about an interlocutor's dispositional and situational knowledge, and (3) the differentiated assessment of an interlocutor's developing understanding of domain knowledge aspects by distinguishing between mechanistic and functional explanatory stances. By discussing the benefits and the limitations of each procedure, this article provides critical reflections on video recall as a versatile research method applied for the analysis of human multimodal behavior in interaction and cognitive processing.}}, author = {{Lazarov, Stefan Teodorov and Schaffer, Michael and Gladow, Viviane and Buschmeier, Hendrik and Buhl, Heike M. and Grimminger, Angela}}, pages = {{29}}, title = {{{Retrospective video recall for analyzing cognitive processes in naturalistic explanations}}}, year = {{2026}}, } @inproceedings{64914, abstract = {{We investigate how verbal and nonverbal linguistic features, exhibited by speakers and listeners in dialogue, can contribute to predicting the listener's state of understanding in explanatory interactions on a moment-by-moment basis. Specifically, we examine three linguistic cues related to cognitive load and hypothesised to correlate with listener understanding: the information value (operationalised with surprisal) and syntactic complexity of the speaker's utterances, and the variation in the listener's interactive gaze behaviour. Based on statistical analyses of the MUNDEX corpus of face-to-face dialogic board game explanations, we find that individual cues vary with the listener's level of understanding. Listener states (‘Understanding’, ‘Partial Understanding’, ‘Non-Understanding’ and ‘Misunderstanding’) were self-annotated by the listeners using a retrospective video-recall method. The results of a subsequent classification experiment, involving two off-the-shelf classifiers and a fine-tuned German BERT-based multimodal classifier, demonstrate that prediction of these four states of understanding is generally possible and improves when the three linguistic cues are considered alongside textual features.}}, author = {{Wang, Yu and Türk, Olcay and Grimminger, Angela and Buschmeier, Hendrik}}, booktitle = {{Proceedings of the 15th Language Resources and Evaluation Conference}}, location = {{Palma, Mallorca, Spain}}, pages = {{11368--11378}}, publisher = {{ELRA}}, title = {{{Predicting states of understanding in explanatory interactions using cognitive load-related linguistic cues}}}, doi = {{10.63317/4tsmsshhd3ad}}, year = {{2026}}, } @article{65565, abstract = {{Abstract Gaze behavior, being continuously accessible to interlocutors in face-to-face interactions, serves as a cue for managing turn-taking, regulating the duration of topical sequences, and supporting cognitive processing in various everyday conversational contexts. The present study seeks to enhance the understanding of the relation between two forms of interactive gaze behavior – gaze aversions and mutual gaze – and the topical development in the explanatory discourse. To do so, we analyzed 24 dyadic board game explanations in which one explainer subsequently explained a board game to three different explainees while the board game was physically absent from the shared space. The main objective of the present study was to investigate the relation of gaze aversions and mutual gaze to the topical development of explanations. For this, based on previous research (Lazarov et al., 2024; Rossano, 2012) we hypothesized that (1) gaze aversions are more likely to be associated with topic changes than topic continuations, and that (2) mutual gaze is more likely to be associated with topic continuations than topic changes. In addition, we explored how the two forms of gaze behavior are related to the interlocutor who initiates a topic change or continuation. Our proportional analysis using a Generalized linear mixed effects model revealed that gaze aversions are related to topic changes initiated by both interlocutors. In contrast, the analysis did not reveal a significant relation between mutual gaze and topic continuations, which could be explained by the feedback elicitation function of mutual gaze at the end of speakers’ utterances (Bavelas et al., 2002; Brône et al., 2017; Kendon, 1967) while monitoring the addressees’ understanding (Clark & Krych, 2004) and the complexity of the analyzed fixed and random effects.}}, author = {{Lazarov, Stefan Teodorov and Grimminger, Angela}}, issn = {{0191-5886}}, journal = {{Journal of Nonverbal Behavior}}, publisher = {{Springer Science and Business Media LLC}}, title = {{{How are gaze aversions and mutual gaze related to the topical development of dyadic explanatory interactions?}}}, doi = {{10.1007/s10919-026-00512-8}}, year = {{2026}}, } @techreport{65789, author = {{Rohlfing, Katharina J. and Steinhardt, Isabel and Scharlau, Ingrid and Schaper, Niclas and Holtfreter, Susan and Biere, Lea and Grimminger, Angela and Schmidt, Rebecca and Festner, Dagmar Franziska and Schmidt, Rebekka and Buhl, Heike M. and Mindt, Ilka and Karsten, Andrea Ramona and Neiske, Iris and Luft, Sebastian}}, title = {{{(Nicht)Nutzung von KI-Werkzeugen in der Lehre: ein Reflexionspapier}}}, doi = {{10.17619/UNIPB/1-2576}}, year = {{2026}}, } @inproceedings{66106, abstract = {{Multimodal backchannels are fundamental to conversational grounding and understanding. However, backchannels do not always transparently reflect the interlocutor's actual cognitive state. “Incongruent backchannels”, where the observable feedback implies understanding although there is no genuine understanding, are a potential source of ambiguity in any interaction. Using acoustic, head movement, and discourse-related data from 45 naturalistic dyadic interactions, we investigate whether incongruent and congruent backchannels show systematically different properties using a classification task. Results show that these backchannels are indeed separable based on multimodal features. Incongruent backchannels are typically characterised by more neutral head movement configurations and lower acoustic dynamism, while discursive cues strongly influence the classification. Overall, the findings suggest a relatively reduced effort in the signalling of incongruent backchannels.}}, author = {{Türk, Olcay and Lazarov, Stefan Teodorov and Wang, Yu and Grimminger, Angela and Buschmeier, Hendrik and Wagner, Petra}}, booktitle = {{Proceedings of INTERSPEECH 2026}}, location = {{Sydney, Australia}}, title = {{{When “yeah” means “not quite”: Multimodal detection of backchannels expressing incomplete understanding}}}, year = {{2026}}, } @misc{61429, author = {{Buschmeier, Hendrik and Grimminger, Angela and Wagner, Petra and Lazarov, Stefan Teodorov and Türk, Olcay and Wang, Yu}}, publisher = {{LibreCat University}}, title = {{{MUNDEX Annotations}}}, doi = {{10.5281/ZENODO.17129817}}, year = {{2025}}, } @article{61156, abstract = {{Explainability has become an important topic in computer science and artificial intelligence, leading to a subfield called Explainable Artificial Intelligence (XAI). The goal of providing or seeking explanations is to achieve (better) ‘understanding’ on the part of the explainee. However, what it means to ‘understand’ is still not clearly defined, and the concept itself is rarely the subject of scientific investigation. This conceptual article aims to present a model of forms of understanding for XAI-explanations and beyond. From an interdisciplinary perspective bringing together computer science, linguistics, sociology, philosophy and psychology, a definition of understanding and its forms, assessment, and dynamics during the process of giving everyday explanations are explored. Two types of understanding are considered as possible outcomes of explanations, namely enabledness, ‘knowing how’ to do or decide something, and comprehension, ‘knowing that’ – both in different degrees (from shallow to deep). Explanations regularly start with shallow understanding in a specific domain and can lead to deep comprehension and enabledness of the explanandum, which we see as a prerequisite for human users to gain agency. In this process, the increase of comprehension and enabledness are highly interdependent. Against the background of this systematization, special challenges of understanding in XAI are discussed.}}, author = {{Buschmeier, Hendrik and Buhl, Heike M. and Kern, Friederike and Grimminger, Angela and Beierling, Helen and Fisher, Josephine Beryl and Groß, André and Horwath, Ilona and Klowait, Nils and Lazarov, Stefan Teodorov and Lenke, Michael and Lohmer, Vivien and Rohlfing, Katharina and Scharlau, Ingrid and Singh, Amit and Terfloth, Lutz and Vollmer, Anna-Lisa and Wang, Yu and Wilmes, Annedore and Wrede, Britta}}, journal = {{Cognitive Systems Research}}, keywords = {{understanding, explaining, explanations, explainable, AI, interdisciplinarity, comprehension, enabledness, agency}}, title = {{{Forms of Understanding for XAI-Explanations}}}, doi = {{10.1016/j.cogsys.2025.101419}}, volume = {{94}}, year = {{2025}}, } @inproceedings{61154, author = {{Türk, Olcay and Lazarov, Stefan Teodorov and Buschmeier, Hendrik and Wagner, Petra and Grimminger, Angela}}, booktitle = {{LingCologne 2025 – Book of Abstracts}}, location = {{Cologne, Germany}}, pages = {{36}}, title = {{{Acoustic detection of false positive backchannels of understanding in explanations}}}, year = {{2025}}, } @misc{65564, author = {{Lazarov, Stefan Teodorov and Türk, Olcay and Grimminger, Angela and Wagner, Petra and Buschmeier, Hendrik}}, publisher = {{LibreCat University}}, title = {{{Annotation Schemes Project A02 "Monitoring the understanding of explanations"}}}, doi = {{10.17605/OSF.IO/J2DHA}}, year = {{2025}}, } @inproceedings{57204, abstract = {{In this study on the use of gesture deixis during explanations, a sample of 24 videorecorded dyadic interactions of a board game explanation was analyzed. The relation between the use of gesture deixis by different explainers and their interpretation of explainees' understanding was investigated. In addition, we describe explainers' intra-individual variations related to their interactions with three different explainees consecutively. While we did not find a relation between interpretations of explainees' complete understanding and a decrease in explainers' use of gesture deixis, we demonstrated that the overall use of gesture deixis is related to the process of interactional monitoring and the attendance of a different explainee.}}, author = {{Lazarov, Stefan Teodorov and Grimminger, Angela}}, booktitle = {{Proceedings of the Annual Meeting of the Cognitive Science Society}}, keywords = {{explanation, gesture deixis, monitoring, understanding}}, location = {{Rotterdam}}, title = {{{Variations in explainers’ gesture deixis in explanations related to the monitoring of explainees’ understanding}}}, volume = {{46}}, year = {{2024}}, } @article{59888, abstract = {{Everyday explanations are interactive processes with the aim to provide a less knowledgeable person with reasonable information about other people, objects, or events. Because explanations are interactive communicative processes, the topical structure of an explanation may vary dynamically depending on the immediate feedback of the explainee. In this paper, we analyse topical transitions in medical explanations organised by different physicians (explainers) related to different forms of multimodal behaviour of caregivers (explainees) attending an explanation about the procedures of an upcoming surgery of a child. The analyses reveal that explainees’ multimodal behaviour with gaze shifts (and particularly gaze aversion) can predict a transition from an elaborated topic to a new one, whereas explainees’ forms of multimodal behaviour with static gaze cannot be related to changes of the topical structure.}}, author = {{Lazarov, Stefan Teodorov and Biermeier, Kai and Grimminger, Angela}}, issn = {{1572-0381}}, journal = {{Interaction Studies}}, keywords = {{explanations, multimodal behaviour, elaborations, conditional probabilities}}, number = {{3}}, pages = {{257 -- 280}}, publisher = {{John Benjamins}}, title = {{{Changes in the topical structure of explanations are related to explainees’ multimodal behaviour}}}, doi = {{10.1075/is.23033.laz}}, volume = {{25}}, year = {{2024}}, } @article{58708, abstract = {{Research about explanation processes is gaining relevance because of the increased popularity of artificial systems required to explain their function or outcome. Following an interactive approach, not only explainers, but also explainees contribute to successful interactions. However, little is known about how explainees actively guide explanation processes and how their involvement relates to learning. We explored the occurrence and type of explainees’ questions in 20 adult — adult explanation dialogues about unknown present and absent objects. Crucially, we related the question types to the explainees’ subsequent recall of the unknown object labels. We found that explainees asked different types of questions, especially about the object’s label and facts. Questions about the object’s function were asked more when objects were present. In addition, requests for labelling were linked to better recall. The results contribute to designing explainable AI that aims to provide relevant and adaptive explanations and to further experimental approaches to study explanations.}}, author = {{Fisher, Josephine Beryl and Rohlfing, Katharina J. and Donnellan, Ed and Grimminger, Angela and Gu, Yan and Vigliocco, Gabriella}}, journal = {{Interaction Studies}}, number = {{2}}, pages = {{244--255}}, publisher = {{John Benjamins}}, title = {{{ Explain with, rather than explain to: How explainees shape their own learning}}}, doi = {{doi.org/10.1075/is.23019.fis}}, volume = {{25}}, year = {{2024}}, } @inproceedings{55912, abstract = {{In explanatory interactions, explainees are expected to continuously provide feedback to explainers by signaling whether they understand an ongoing explanation. The study presented in this paper is based on the hypothesis that explainees use a set of multimodal cues, including vocalizations, facial expressions, and movements of the torso, head, and hands, to do so. We test this hypothesis by building a random forest classifier based on a multimodal corpus of dyadic explanations (21 explainers and explainees), in which windows of understanding or non-understanding were identified by participants in a retrospective video recall task. Results show that sequences of understanding can indeed be differentiated from those of non-understanding, and that a diverse set of predictors covering a wide range of modalities contributes to this classification. Due to data sparsity and a high degree of individual variation, the generalizability of our results is currently limited, but they support our hypothesis of the relevance of multimodal display in explanatory interactions.}}, author = {{Türk, Olcay and Lazarov, Stefan Teodorov and Wang, Yu and Buschmeier, Hendrik and Grimminger, Angela and Wagner, Petra}}, booktitle = {{Proceedings of the 26th ACM International Conference on Multimodal Interaction}}, location = {{San José, Costa Rica}}, pages = {{449--458}}, title = {{{Predictability of understanding in explanatory interactions based on multimodal cues}}}, doi = {{10.1145/3678957.3685741}}, year = {{2024}}, } @article{37074, abstract = {{Pointing is one of the first conventional means of communication and infants have various motives for engaging in it such as imperative, declarative, or informative. Little is known about the developmental paths of producing and understanding these different motives. In our longitudinal study (N = 58) during the second year of life, we experimentally elicited infants’ pointing production and comprehension in various settings and under pragmatically valid conditions. We followed two steps in our analyses and assessed the occurrence of canonical index-finger pointing for different motives and the engagement in an ongoing interaction in pursuit of a joint goal revealed by frequency and multimodal utterances. For understanding the developmental paths, we compared two groups: typically developing infants (TD) and infants who have been assessed as having delayed language development (LD). Results showed that the developmental paths differed according to the various motives. When comparing the two groups, for all motives, LD infants produced index-finger pointing 2 months later than TD infants. For the engagement, although the pattern was less consistent across settings, the frequency of pointing was comparable in both groups, but infants with LD used less canonical forms of pointing and made fewer multimodal contributions than TD children.}}, author = {{Rohlfing, Katharina J. and Lüke, Carina and Liszkowski, Ulf and Ritterfeld, Ute and Grimminger, Angela}}, issn = {{1660-4601}}, journal = {{International Journal of Environmental Research and Public Health}}, keywords = {{Health, Toxicology and Mutagenesis, Public Health, Environmental and Occupational Health}}, number = {{9}}, publisher = {{MDPI AG}}, title = {{{Developmental Paths of Pointing for Various Motives in Infants with and without Language Delay}}}, doi = {{10.3390/ijerph19094982}}, volume = {{19}}, year = {{2022}}, }