@inproceedings{walker2026_114436,
  title = {Conv-BDI: An Extension of the BDI Framework for Conversational Agents},
  author = {Walker, Nicholas Thomas and Wagner, Nicolas and Hilgendorf, Laetitia and Ultes, Stefan},
  year = {2026},
  pages = {104–114},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-114436x},
  url = {https://fis.uni-bamberg.de/handle/uniba/114436},
  language = {eng},
  abstract = {With the large and increasing variety of architectures for conversational agent design, there is a need to investigate the necessary elements of practical conversational agents in light of new technologies. To address this need, we introduce a new abstract framework of conversational agents design which we call Conv-BDI. The BDI model is a longestablished theory of decision-making in artificial agents, which the Conv-BDI model extends to describe the design of conversational agents from traditional symbolic logic-based models or statistical models to more recent LLM-based agents. Specifically, we extend the core BDI model with notions of Purpose and Behavioral Guidelines, while also elaborating on the role of system actions within this framework. The Conv-BDI model thus provides a framework of intentionality in conversational agents that can be applied to to design of contemporary conversational agents.},
  keywords = {-}
}

@inproceedings{feustel2026_114438,
  title = {Enhancing Model Transparency : A Dialogue System Approach to XAI with Domain Knowledge},
  author = {Feustel, Isabel and Rach, Niklas and Minker, Wolfgang and Ultes, Stefan},
  year = {2026},
  pages = {248-258},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-114438x},
  url = {https://fis.uni-bamberg.de/handle/uniba/114438},
  language = {eng},
  abstract = {Explainable artifcial intelligence (XAI) is
a rapidly evolving feld that seeks to create
AI systems that can provide humanunderstandable
explanations for their decisionmaking
processes. However, these explanations
rely on model and data-specifc information
only. To support better human decisionmaking,
integrating domain knowledge into AI
systems is expected to enhance understanding
and transparency. In this paper, we present
an approach for combining XAI explanations
with domain knowledge within a dialogue system.
We concentrate on techniques derived
from the feld of computational argumentation
to incorporate domain knowledge and corresponding
explanations into human-machine dialogue.
We implement the approach in a prototype
system for an initial user evaluation, where
users interacted with the dialogue system to receive
predictions from an underlying AI model.
The participants were able to explore different
types of explanations and domain knowledge.
Our results indicate that users tend to more
effectively evaluate model performance when
domain knowledge is integrated. On the other
hand, we found that domain knowledge was
not frequently requested by the user during dialogue
interactions.},
  keywords = {-}
}

@inproceedings{wagner2026_114437,
  title = {On the Controllability of Large Language Models for Dialogue Interaction},
  author = {Wagner, Nicolas and Ultes, Stefan},
  year = {2026},
  pages = {216-221},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-114437x},
  url = {https://fis.uni-bamberg.de/handle/uniba/114437},
  language = {eng},
  abstract = {This paper investigates the enhancement of Dialogue Systems by integrating the creative capabilities of Large Language Models. While traditional Dialogue Systems focus on understanding user input and selecting appropriate system actions, Language Models excel at generating natural language text based on prompts. Therefore, we propose to improve controllability and coherence of interactions by guiding a Language Model with control signals that enable explicit control over the system behaviour. To address this, we tested and evaluated our concept in 815 conversations with over 3600 dialogue exchanges on a dataset. Our experiment examined the quality of generated system responses using two strategies: An unguided strategy where task data was provided to the models, and a controlled strategy in which a simulated Dialogue Controller provided appropriate system actions. The results show that the average BLEU score and the classifcation of dialogue acts improved in the controlled Natural Language Generation.},
  keywords = {-}
}

@inproceedings{aicher2025_110658,
  title = {The Influence of Avatar Interfaces on Argumentative Dialogues},
  author = {Aicher, Annalena and Weber, Klaus and André, Elisabeth and Minker, Wolfgang and Ultes, Stefan},
  year = {2025},
  pages = {1-8},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-110658x},
  url = {https://fis.uni-bamberg.de/handle/uniba/110658},
  language = {eng},
  abstract = {Humans form opinions and justify different points of view by ex- changing arguments and knowledge.  Likewise to human-human interaction, the way arguments are presented infuence the user’s  willingness to engage into a critical refection. Especially when interacting with conversational  agents the user’s engagement and motivation are important factors and highly infuence the success  or failure of such a mixed team. To maintain the users’ trust and satis- faction, the users’  perception of the respective system is an important indicator. Thus, this work investigates the  design of a cooperative argumentative dialogue system using a virtual avatar compared to a  non-avatar interface by evaluating a crowdsourcing study conducted with 84 participants. The  results indicate, that the avatar system is perceived as signifcantly more appealing and natural  and thus, engaging which also infuences the acceptance and perception of the quality of presented  arguments. Furthermore, we found that the presence of the avatar often led to an increase in the  anticipated level of conversational profciency similar to that of a human interlocutor. Therefore, 
this work provides important insights for the design of future cooperative argumentative virtual avatar interfaces.},
  keywords = {Conversational Engagement, User Trust, Avatar Interface, Human-Computer Interaction, Crowdsourcing Study}
}

@inproceedings{aicher2025_110816,
  title = {BEA : Building Engaging Argumentation},
  author = {Aicher, Annalena and Weber, Klaus and André, Elisabeth and Minker, Wolfgang and Ultes, Stefan},
  year = {2025},
  pages = {279-295},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-110816x},
  url = {https://fis.uni-bamberg.de/handle/uniba/110816},
  language = {eng},
  abstract = {Exchanging arguments and knowledge in conversations is an intuitive way for humans to form opinions and reconcile opposing viewpoints. The vast amount of information available on the internet, often accessed through search engines, presents a considerable challenge. Managing and filtering this overwhelming wealth of data raises the potential for intellectual isolation. This can stem either from personalized searches that create “filter bubbles” by considering a user’s history and preferences, or from the intrinsic, albeit unconscious, tendency of users to seek information that aligns with their existing beliefs, forming “self-imposed filter bubbles”.

To address this issue, we introduce a model aimed at engaging the user in a critical examination of presented arguments and propose the use of a virtual agent engaging in a deliberative dialogue with human users to facilitate a fair and unbiased opinion formation. Our experiments have demonstrated the success of these models and their implementation. As a result, this work offers valuable insights for the design of future cooperative argumentative dialogue systems.},
  keywords = {Cooperative Argumentative Dialogue Systems, Reflective (User) Engagement (RUE), Conversational Engagement, User Attention, User Focus, Gaze Tracking, Virtual Avatar}
}

@inproceedings{walker2025_110385,
  title = {Conv-BDI: An Extension of the BDI Framework for Conversational Agents},
  author = {Walker, Nicholas Thomas and Wagner, Nicolas and Hilgendorf, Laetitia and Ultes, Stefan},
  year = {2025},
  booktitle = {Proceedings of the 29th Workshop on the Semantics and Pragmatics of Dialogue – Full Papers},
  pages = {104–114},
  publisher = {SEMDIAL},
  address = {Bielefeld},
  url = {https://fis.uni-bamberg.de/handle/uniba/110385},
  language = {eng},
  abstract = {With the large and increasing variety of architectures for conversational agent design, there is a need to investigate the necessary elements of practical conversational agents in light of new technologies. To address this need, we introduce a new abstract framework of conversational agents design which we call Conv-BDI. The BDI model is a longestablished theory of decision-making in artificial agents, which the Conv-BDI model extends to describe the design of conversational agents from traditional symbolic logic-based models or statistical models to more recent LLM-based agents. Specifically, we extend the core BDI model with notions of Purpose and Behavioral Guidelines, while also elaborating on the role of system actions within this framework. The Conv-BDI model thus provides a framework of intentionality in conversational agents that can be applied to to design of contemporary conversational agents.},
  keywords = {-}
}

@article{aicher2025_107706,
  title = {Enhancing Reflective and Conversational User Engagement in Argumentative Dialogues with Virtual Agents},
  author = {Aicher, Annalena and Matsuda, Yuki and Yasumoto, Keichii and Minker, Wolfgang and André, Elisabeth and Ultes, Stefan},
  year = {2025},
  pages = {1-44},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-1077069},
  url = {https://fis.uni-bamberg.de/handle/uniba/107706},
  language = {eng},
  abstract = {In their process of information seeking, human users tend to selectively ignore information that contradicts their pre-existing beliefs or opinions. These so-called “self-imposed flter bubbles” (SFBs) pose a signifcant challenge for argumentative conversational agents aiming to facilitate critical, unbiased opinion formation on controversial topics. With the ultimate goal of developing a system that helps users break their self-imposed flter bubbles (SFBs), this paper aims to investigate the role of co-speech gestures, specifcally examining how these gestures signifcantly contribute to achieving this objective. This paper extends current research by examining methods to engage users in cooperative discussions with a virtual human-like agent, encouraging a deep refection on arguments to disrupt SFBs. Specifcally, we investigate the agent’s non-verbal behavior in the form of co-speech gestures. We analyze whether co-speech gestures, depending on the conveyed information, enhance motivation, and thus conversational user engagement, thereby encouraging users to consider information that could potentially disrupt their SFBs. The fndings of a laboratory study with 56 participants highlight the importance of non-verbal agent behaviors, such as co-speech gestures, in improving users’ perceptions of the interaction and the conveyed content. This effect is particularly notable when the content aims to challenge the user’s SFB. Therefore, this research offers valuable insights into enhancing user engagement in the design of multimodal interactions with future cooperative argumentative virtual agents.},
  keywords = {non-verbal agent behavior, virtual agents, co-speech gestures, user interest, confirmation bias, self-imposed filter bubbles (SFB), argumentative dialogue systems (ADS), human–agent interaction}
}

@inproceedings{aicher2024_110388,
  title = {Exploring the Impact of Non-Verbal Virtual Agent Behavior on User Engagement in Argumentative Dialogues},
  author = {Aicher, Annalena Bea and Matsuda, Yuki and Yasumoto, Keichii and Minker, Wolfgang and André, Elisabeth and Ultes, Stefan},
  year = {2024},
  publisher = {arXiv},
  doi = {10.48550/arxiv.2411.11102},
  url = {https://fis.uni-bamberg.de/handle/uniba/110388},
  language = {eng}
}

@inproceedings{feustel2024_110387,
  title = {Enhancing Model Transparency : A Dialogue System Approach to XAI with Domain Knowledge},
  author = {Feustel, Isabel and Rach, Niklas and Minker, Wolfgang and Ultes, Stefan},
  year = {2024},
  booktitle = {Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue},
  pages = {248-258},
  publisher = {Association for Computational Linguistics},
  address = {Kyoto},
  doi = {10.18653/v1/2024.sigdial-1.22},
  url = {https://fis.uni-bamberg.de/handle/uniba/110387},
  language = {eng},
  abstract = {Explainable artifcial intelligence (XAI) is
a rapidly evolving feld that seeks to create
AI systems that can provide humanunderstandable
explanations for their decisionmaking
processes. However, these explanations
rely on model and data-specifc information
only. To support better human decisionmaking,
integrating domain knowledge into AI
systems is expected to enhance understanding
and transparency. In this paper, we present
an approach for combining XAI explanations
with domain knowledge within a dialogue system.
We concentrate on techniques derived
from the feld of computational argumentation
to incorporate domain knowledge and corresponding
explanations into human-machine dialogue.
We implement the approach in a prototype
system for an initial user evaluation, where
users interacted with the dialogue system to receive
predictions from an underlying AI model.
The participants were able to explore different
types of explanations and domain knowledge.
Our results indicate that users tend to more
effectively evaluate model performance when
domain knowledge is integrated. On the other
hand, we found that domain knowledge was
not frequently requested by the user during dialogue
interactions.},
  keywords = {-}
}

@inproceedings{wagner2024_110386,
  title = {On the Controllability of Large Language Models for Dialogue Interaction},
  author = {Wagner, Nicolas and Ultes, Stefan},
  year = {2024},
  booktitle = {Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue},
  pages = {216-221},
  publisher = {Association for Computational Linguistics},
  address = {Kyoto},
  doi = {10.18653/v1/2024.sigdial-1.19},
  url = {https://fis.uni-bamberg.de/handle/uniba/110386},
  language = {eng},
  abstract = {This paper investigates the enhancement of Dialogue Systems by integrating the creative capabilities of Large Language Models. While traditional Dialogue Systems focus on understanding user input and selecting appropriate system actions, Language Models excel at generating natural language text based on prompts. Therefore, we propose to improve controllability and coherence of interactions by guiding a Language Model with control signals that enable explicit control over the system behaviour. To address this, we tested and evaluated our concept in 815 conversations with over 3600 dialogue exchanges on a dataset. Our experiment examined the quality of generated system responses using two strategies: An unguided strategy where task data was provided to the models, and a controlled strategy in which a simulated Dialogue Controller provided appropriate system actions. The results show that the average BLEU score and the classifcation of dialogue acts improved in the controlled Natural Language Generation.},
  keywords = {-}
}

@inproceedings{kawahara2024_110384,
  title = {Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue},
  editor = {Kawahara, Tatsuya and Demberg, Vera and Ultes, Stefan and Inoue, Koji and Mehri, Shikib and Howcroft, David and Komatani, Kazunori},
  year = {2024},
  publisher = {Association for Computational Linguistics},
  address = {Kyoto, Japan},
  doi = {10.18653/v1/2024.sigdial-1},
  url = {https://fis.uni-bamberg.de/handle/uniba/110384},
  language = {eng}
}

@article{aicher2024_97134,
  title = {Enhancing Reflective and Conversational User Engagement in Argumentative Dialogues with Virtual Agents},
  author = {Aicher, Annalena and Matsuda, Yuki and Yasumoto, Keichii and Minker, Wolfgang and André, Elisabeth and Ultes, Stefan},
  year = {2024},
  journal = {Multimodal technologies and interaction},
  volume = {8},
  number = {71},
  publisher = {MDPI AG},
  address = {Basel},
  issn = {2414-4088},
  doi = {10.3390/mti8080071},
  url = {https://fis.uni-bamberg.de/handle/uniba/97134},
  language = {eng},
  abstract = {In their process of information seeking, human users tend to selectively ignore information that contradicts their pre-existing beliefs or opinions. These so-called “self-imposed flter bubbles” (SFBs) pose a signifcant challenge for argumentative conversational agents aiming to facilitate critical, unbiased opinion formation on controversial topics. With the ultimate goal of developing a system that helps users break their self-imposed flter bubbles (SFBs), this paper aims to investigate the role of co-speech gestures, specifcally examining how these gestures signifcantly contribute to achieving this objective. This paper extends current research by examining methods to engage users in cooperative discussions with a virtual human-like agent, encouraging a deep refection on arguments to disrupt SFBs. Specifcally, we investigate the agent’s non-verbal behavior in the form of co-speech gestures. We analyze whether co-speech gestures, depending on the conveyed information, enhance motivation, and thus conversational user engagement, thereby encouraging users to consider information that could potentially disrupt their SFBs. The fndings of a laboratory study with 56 participants highlight the importance of non-verbal agent behaviors, such as co-speech gestures, in improving users’ perceptions of the interaction and the conveyed content. This effect is particularly notable when the content aims to challenge the user’s SFB. Therefore, this research offers valuable insights into enhancing user engagement in the design of multimodal interactions with future cooperative argumentative virtual agents.},
  keywords = {non-verbal agent behavior, virtual agents, co-speech gestures, user interest, confirmation bias, self-imposed filter bubbles (SFB), argumentative dialogue systems (ADS), human–agent interaction}
}

@inproceedings{aicher2024_96623,
  title = {BEA : Building Engaging Argumentation},
  author = {Aicher, Annalena and Weber, Klaus and André, Elisabeth and Minker, Wolfgang and Ultes, Stefan},
  year = {2024},
  booktitle = {Robust Argumentation Machines : First International Conference, RATIO 2024, Bielefeld, Germany, June 5–7, 2024, Proceedings},
  pages = {279-295},
  publisher = {Springer Nature Switzerland},
  address = {Cham},
  isbn = {978-3-031-63535-9},
  doi = {10.1007/978-3-031-63536-6\_17},
  url = {https://fis.uni-bamberg.de/handle/uniba/96623},
  language = {eng},
  abstract = {Exchanging arguments and knowledge in conversations is an intuitive way for humans to form opinions and reconcile opposing viewpoints. The vast amount of information available on the internet, often accessed through search engines, presents a considerable challenge. Managing and filtering this overwhelming wealth of data raises the potential for intellectual isolation. This can stem either from personalized searches that create “filter bubbles” by considering a user’s history and preferences, or from the intrinsic, albeit unconscious, tendency of users to seek information that aligns with their existing beliefs, forming “self-imposed filter bubbles”.

To address this issue, we introduce a model aimed at engaging the user in a critical examination of presented arguments and propose the use of a virtual agent engaging in a deliberative dialogue with human users to facilitate a fair and unbiased opinion formation. Our experiments have demonstrated the success of these models and their implementation. As a result, this work offers valuable insights for the design of future cooperative argumentative dialogue systems.},
  keywords = {Cooperative Argumentative Dialogue Systems, Reflective (User) Engagement (RUE), Conversational Engagement, User Attention, User Focus, Gaze Tracking, Virtual Avatar}
}

@inproceedings{aicher2024_94787,
  title = {Towards Breaking the Self-imposed Filter Bubble in Argumentative Dialogues},
  author = {Aicher, Annalena and Kornmueller, Daniel and Matsuda, Yuki and Ultes, Stefan and Minker, Wolfgang and Yasumoto, Keiichi},
  year = {2024},
  pages = {593–604},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-947872},
  url = {https://fis.uni-bamberg.de/handle/uniba/94787},
  language = {eng},
  abstract = {Human users tend to selectively ignore information that contradicts their pre-existing beliefs or opinions in their process of information seeking. These “self-imposed filter bubbles” (SFB) pose a significant challenge for cooperative argumentative dialogue systems aiming to build an unbiased opinion and a better understanding of the topic at hand. To address this issue, we develop a strategy for overcoming users’ SFB within the course of the interaction. By continuously modeling the user’s position in relation to the SFB, we are able to identify the respective arguments which maximize the probability to get outside the SFB and present them to the user. We implemented this approach in an argumentative dialogue system and evaluated in a laboratory user study with 60 participants to show its validity and applicability. The findings suggest that the strategy was successful in breaking users’ SFBs and promoting a more reflective and comprehensive discussion of the topic.},
  keywords = {Self-imposed Filter Bubble}
}

@inproceedings{aicher2024_93277,
  title = {Self-imposed Filter Bubble Model for Argumentative Dialogues},
  author = {Aicher, Annalena and Kornmüller, Daniel and Minker, Wolfgang and Ultes, Stefan},
  year = {2024},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-932771},
  url = {https://fis.uni-bamberg.de/handle/uniba/93277},
  language = {eng},
  abstract = {During their information seeking people tend to filter out all the parts of the available information that do not fit their existing beliefs or opinions. In this paper we present a model for this “Self-imposed Filter Bubble” (SFB) consisting of four dimensions. Thereby, we aim to 1) estimate the probability of the user being caught in an SFB and consequently, 2) identify suitable clues to reduce this probability in the further course of a dialogue. Using an exemplary implementation in an argumentative dialogue system, we demonstrate the validity and applicability of this model in an online user study with 102 participants. These findings serve as a basis for developing a system strategy to break the user’s SFB and contribute to a sustainable and profound reflection on a topic from all viewpoints.},
  keywords = {Confirmation Bias, Echo Chambers, User Modeling, Computational Argumentation, Cooperative Argumentative Dialogue Systems (ADS)}
}

@inproceedings{aicher2023_96550,
  title = {The Influence of Avatar Interfaces on Argumentative Dialogues},
  author = {Aicher, Annalena and Weber, Klaus and André, Elisabeth and Minker, Wolfgang and Ultes, Stefan},
  year = {2023},
  booktitle = {IVA '23: Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents},
  pages = {1-8},
  publisher = {Association for Computing Machinery},
  address = {New York},
  isbn = {978-1-4503-9994-4},
  doi = {10.1145/3570945.3607343},
  url = {https://fis.uni-bamberg.de/handle/uniba/96550},
  language = {eng},
  abstract = {Humans form opinions and justify different points of view by ex- changing arguments and knowledge.  Likewise to human-human interaction, the way arguments are presented infuence the user’s  willingness to engage into a critical refection. Especially when interacting with conversational  agents the user’s engagement and motivation are important factors and highly infuence the success  or failure of such a mixed team. To maintain the users’ trust and satis- faction, the users’  perception of the respective system is an important indicator. Thus, this work investigates the  design of a cooperative argumentative dialogue system using a virtual avatar compared to a  non-avatar interface by evaluating a crowdsourcing study conducted with 84 participants. The  results indicate, that the avatar system is perceived as signifcantly more appealing and natural  and thus, engaging which also infuences the acceptance and perception of the quality of presented  arguments. Furthermore, we found that the presence of the avatar often led to an increase in the  anticipated level of conversational profciency similar to that of a human interlocutor. Therefore, 
this work provides important insights for the design of future cooperative argumentative virtual avatar interfaces.},
  keywords = {Conversational Engagement, User Trust, Avatar Interface, Human-Computer Interaction, Crowdsourcing Study}
}

@inproceedings{aicher2023_91882,
  title = {Evaluating a Spoken Argumentative Dialogue System},
  author = {Aicher, Annalena and Hillmann, Stefan and Michael, Thilo and Möller, Sebastian and Minker, Wolfgang and Ultes, Stefan},
  year = {2023},
  booktitle = {Social Computing and Social Media Social Computing and Social Media : 15th International Conference, SCSM 2023, Held as Part of the 25th HCI International Conference, HCII 2023, Copenhagen, Denmark, July 23–28, 2023, Proceedings},
  pages = {425–434},
  publisher = {Springer Nature Switzerland},
  address = {Cham},
  isbn = {978-3-031-35927-9},
  doi = {10.1007/978-3-031-35927-9\_29},
  url = {https://fis.uni-bamberg.de/handle/uniba/91882},
  language = {eng}
}

@inproceedings{aicher2023_91881,
  title = {Towards Breaking the Self-imposed Filter Bubble in Argumentative Dialogues},
  author = {Aicher, Annalena and Kornmueller, Daniel and Matsuda, Yuki and Ultes, Stefan and Minker, Wolfgang and Yasumoto, Keiichi},
  year = {2023},
  booktitle = {Proceedings of the 24th Meeting of the Special Interest Group on Discourse and Dialogue},
  pages = {593–604},
  publisher = {Association for Computational Linguistics},
  address = {Prague, Czechia},
  doi = {10.18653/v1/2023.sigdial-1.56},
  url = {https://fis.uni-bamberg.de/handle/uniba/91881},
  language = {eng},
  abstract = {Human users tend to selectively ignore information that contradicts their pre-existing beliefs or opinions in their process of information seeking. These “self-imposed filter bubbles” (SFB) pose a significant challenge for cooperative argumentative dialogue systems aiming to build an unbiased opinion and a better understanding of the topic at hand. To address this issue, we develop a strategy for overcoming users’ SFB within the course of the interaction. By continuously modeling the user’s position in relation to the SFB, we are able to identify the respective arguments which maximize the probability to get outside the SFB and present them to the user. We implemented this approach in an argumentative dialogue system and evaluated in a laboratory user study with 60 participants to show its validity and applicability. The findings suggest that the strategy was successful in breaking users’ SFBs and promoting a more reflective and comprehensive discussion of the topic.},
  keywords = {Self-imposed Filter Bubble}
}

@inproceedings{aicher2023_91880,
  title = {Towards Modelling Elaborateness in Argumentative Dialogue Systems},
  author = {Aicher, Annalena and Fuchs, Marc and Minker, Wolfgang and Ultes, Stefan},
  editor = {Degen, Helmut and Ntoa, Stavroula},
  year = {2023},
  booktitle = {Artificial Intelligence in HCI : 4th International Conference, AI-HCI 2023, Held as Part of the 25th HCI International Conference, HCII 2023, Copenhagen, Denmark, July 23–28, 2023, Proceedings, Part II},
  pages = {3–22},
  publisher = {Springer Nature Switzerland},
  address = {Cham},
  isbn = {978-3-031-35894-4},
  doi = {10.1007/978-3-031-35894-4\_1},
  url = {https://fis.uni-bamberg.de/handle/uniba/91880},
  language = {eng}
}

@inproceedings{liu2023_91841,
  title = {Unified Conversational Models with System-Initiated Transitions between Chit-Chat and Task-Oriented Dialogues},
  author = {Liu, Ye and Ultes, Stefan and Minker, Wolfgang and Maier, Wolfgang},
  year = {2023},
  booktitle = {CUI '23: Proceedings of the 5th International Conference on Conversational User Interfaces},
  pages = {1-9},
  publisher = {Association for Computing Machinery},
  address = {New York NY, United States},
  isbn = {979-8-4007-0014-9},
  doi = {10.1145/3571884.3597125},
  url = {https://fis.uni-bamberg.de/handle/uniba/91841},
  language = {eng}
}

@inproceedings{aicher2023_91843,
  title = {Self-imposed Filter Bubble Model for Argumentative Dialogues},
  author = {Aicher, Annalena and Kornmüller, Daniel and Minker, Wolfgang and Ultes, Stefan},
  year = {2023},
  booktitle = {Proceedings of the 5th International Conference on Conversational User Interfaces},
  publisher = {ACM},
  address = {New York,NY, United States},
  isbn = {979-8-4007-0014-9},
  doi = {10.1145/3571884.3597131},
  url = {https://fis.uni-bamberg.de/handle/uniba/91843},
  language = {eng},
  abstract = {During their information seeking people tend to filter out all the parts of the available information that do not fit their existing beliefs or opinions. In this paper we present a model for this “Self-imposed Filter Bubble” (SFB) consisting of four dimensions. Thereby, we aim to 1) estimate the probability of the user being caught in an SFB and consequently, 2) identify suitable clues to reduce this probability in the further course of a dialogue. Using an exemplary implementation in an argumentative dialogue system, we demonstrate the validity and applicability of this model in an online user study with 102 participants. These findings serve as a basis for developing a system strategy to break the user’s SFB and contribute to a sustainable and profound reflection on a topic from all viewpoints.},
  keywords = {Confirmation Bias, Echo Chambers, User Modeling, Computational Argumentation, Cooperative Argumentative Dialogue Systems (ADS)}
}

@inproceedings{aicher2023_91844,
  title = {Exploring the Mobile Usability of Argumentative Dialogue Systems for Opinion Building},
  author = {Aicher, Annalena and Hillmann, Stefan and Möller, Sebastian and Minker, Wolfgang and Ultes, Stefan},
  editor = {Salvendy, Gavriel},
  year = {2023},
  booktitle = {Design, operation and evaluation of mobile communications : 4th international conference, MOBILE 2023, held as part of the 25th HCI International Conference, HCII 2023, Copenhagen, Denmark, July 23–28, 2023, proceedings},
  pages = {127-143},
  publisher = {Springer},
  address = {Cham, Switzerland},
  isbn = {978-3-031-35920-0},
  doi = {10.1007/978-3-031-35921-7\_9},
  url = {https://fis.uni-bamberg.de/handle/uniba/91844},
  language = {eng}
}

@inproceedings{liu2023_91575,
  title = {System-Initiated Transitions from Chit-Chat to Task-Oriented Dialogues with Transition Info Extractor and Transition Sentence Generator},
  author = {Liu, Ye and Ultes, Stefan and Minker, Wolfgang and Maier, Wolfgang},
  year = {2023},
  pages = {279–292},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-915753},
  url = {https://fis.uni-bamberg.de/handle/uniba/91575},
  language = {eng},
  abstract = {In this work, we study dialogue scenarios that start from chit-chat but eventually switch to task-related services, and investigate how a unified dialogue model, which can engage in both chit-chat and task-oriented dialogues, takes the initiative during the dialogue mode transition from chit-chat to task-oriented in a coherent and cooperative manner. We firstly build a transition info extractor (TIE) that keeps track of the preceding chit-chat interaction and detects the potential user intention to switch to a task-oriented service. Meanwhile, in the unified model, a transition sentence generator (TSG) is extended through efficient Adapter tuning and transition prompt learning. When the TIE successfully finds task-related information from the preceding chit-chat, such as a transition domain (“train” in Figure fig: system-initiated transition from chit-chat to task-oriented.), then the TSG is activated automatically in the unified model to initiate this transition by generating a transition sentence under the guidance of transition information extracted by TIE. The experimental results show promising performance regarding the proactive transitions. We achieve an additional large improvement on TIE model by utilizing Conditional Random Fields (CRF). The TSG can flexibly generate transition sentences while maintaining the unified capabilities of normal chit-chat and task-oriented response generation.},
  keywords = {System-Initiated Transitions}
}

@inproceedings{liu2023_91204,
  title = {Unified Conversational Models with System-Initiated Transitions between Chit-Chat and Task-Oriented Dialogues},
  author = {Liu, Ye and Minker, Wolfgang and Maier, Wolfgang and Ultes, Stefan},
  year = {2023},
  booktitle = {CUI '23 : Proceedings of the 5th International Conference on Conversational User Interfaces},
  pages = {1-9},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  isbn = {9798400700149},
  doi = {10.1145/3571884.3597125},
  url = {https://fis.uni-bamberg.de/handle/uniba/91204},
  language = {eng}
}

@inproceedings{liu2023_91203,
  title = {System-Initiated Transitions from Chit-Chat to Task-Oriented Dialogues with Transition Info Extractor and Transition Sentence Generator},
  author = {Liu, Ye and Ultes, Stefan and Minker, Wolfgang and Maier, Wolfgang},
  year = {2023},
  booktitle = {Proceedings of the 16th International Natural Language Generation Conference},
  pages = {279–292},
  publisher = {Association for Computational Linguistics},
  address = {Prague, Czechia},
  url = {https://fis.uni-bamberg.de/handle/uniba/91203},
  language = {eng},
  abstract = {In this work, we study dialogue scenarios that start from chit-chat but eventually switch to task-related services, and investigate how a unified dialogue model, which can engage in both chit-chat and task-oriented dialogues, takes the initiative during the dialogue mode transition from chit-chat to task-oriented in a coherent and cooperative manner. We firstly build a transition info extractor (TIE) that keeps track of the preceding chit-chat interaction and detects the potential user intention to switch to a task-oriented service. Meanwhile, in the unified model, a transition sentence generator (TSG) is extended through efficient Adapter tuning and transition prompt learning. When the TIE successfully finds task-related information from the preceding chit-chat, such as a transition domain (“train” in Figure fig: system-initiated transition from chit-chat to task-oriented.), then the TSG is activated automatically in the unified model to initiate this transition by generating a transition sentence under the guidance of transition information extracted by TIE. The experimental results show promising performance regarding the proactive transitions. We achieve an additional large improvement on TIE model by utilizing Conditional Random Fields (CRF). The TSG can flexibly generate transition sentences while maintaining the unified capabilities of normal chit-chat and task-oriented response generation.},
  keywords = {System-Initiated Transitions}
}

@inproceedings{walker2023_59668,
  title = {GraphWOZ: Dialogue Management with Conversational Knowledge Graphs},
  author = {Walker, Nicholas Thomas and Ultes, Stefan and Lison, Pierre},
  year = {2023},
  pages = {1-17},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-596685},
  url = {https://fis.uni-bamberg.de/handle/uniba/59668},
  language = {eng},
  abstract = {We present a new approach to dialogue management using conversational knowledge graphs as core representation of the dialogue state. To this end, we introduce a new dataset, GraphWOZ, which comprises Wizard-of-Oz dialogues in which human participants interact with a robot acting as a receptionist. In contrast to most existing work on dialogue management, GraphWOZ relies on a dialogue state explicitly represented as a dynamic knowledge graph instead of a fixed set of slots. This graph is composed of a varying number of entities (such as individuals, places, events, utterances and mentions) and relations between them (such as persons being part of a group or attending an event). The graph is then regularly updated on the basis of new observations and system actions. GraphWOZ is released along with detailed manual annotations related to the user intents, system responses, and reference relations occurring in both user and system turns. Based on GraphWOZ, we present experimental results for two dialogue management tasks, namely conversational entity linking and response ranking. For conversational entity linking, we show how to connect utterance mentions to their corresponding entity in the knowledge graph with a neural model relying on a combination of both string and graph-based features. Response ranking is then performed by summarizing the relevant content of the graph into a text, which is concatenated with the dialogue history and employed as input to score possible responses to a given dialogue state.},
  keywords = {Dialogue Management, Knowledge Graph}
}

@article{abro2022_59486,
  title = {Natural language understanding for argumentative dialogue systems in the opinion building domain},
  author = {Abro, Waheed Ahmed and Aicher, Annalena and Rach, Niklas and Ultes, Stefan and Minker, Wolfgang and Qi, Guilin},
  year = {2022},
  journal = {Knowledge-Based Systems},
  volume = {242},
  issn = {0950-7051},
  doi = {10.1016/j.knosys.2022.108318},
  url = {https://fis.uni-bamberg.de/handle/uniba/59486},
  language = {eng}
}

@incollection{liu2022_59484,
  title = {Empathetic Dialogue Generation with Pre-trained RoBERTa-GPT2 and External Knowledge},
  author = {Liu, Ye and Maier, Wolfgang and Ultes, Stefan and Minker, Wolfgang},
  year = {2022},
  booktitle = {Conversational AI for Natural Human-Centric Interaction},
  pages = {67-81},
  publisher = {Springer Nature},
  address = {Singapore},
  doi = {10.1007/978-981-19-5538-9\_5},
  url = {https://fis.uni-bamberg.de/handle/uniba/59484},
  language = {eng}
}

@article{miehle2022_59483,
  title = {When to Say What and How: Adapting the Elaborateness and Indirectness of Spoken Dialogue Systems},
  author = {Miehle, Juliana and Minker, Wolfgang and Ultes, Stefan},
  year = {2022},
  journal = {Dialogue \& Discourse},
  volume = {13},
  number = {1},
  pages = {1-40},
  issn = {2152-9620},
  doi = {10.5210/dad.2022.101},
  url = {https://fis.uni-bamberg.de/handle/uniba/59483},
  language = {eng}
}

@inproceedings{walker2022_58420,
  title = {GraphWOZ: Dialogue Management with Conversational Knowledge Graphs},
  author = {Walker, Nicholas Thomas and Ultes, Stefan and Lison, Pierre},
  year = {2022},
  pages = {1-17},
  publisher = {Arxiv.org},
  doi = {10.48550/arXiv.2211.12852},
  url = {https://fis.uni-bamberg.de/handle/uniba/58420},
  language = {eng},
  abstract = {We present a new approach to dialogue management using conversational knowledge graphs as core representation of the dialogue state. To this end, we introduce a new dataset, GraphWOZ, which comprises Wizard-of-Oz dialogues in which human participants interact with a robot acting as a receptionist. In contrast to most existing work on dialogue management, GraphWOZ relies on a dialogue state explicitly represented as a dynamic knowledge graph instead of a fixed set of slots. This graph is composed of a varying number of entities (such as individuals, places, events, utterances and mentions) and relations between them (such as persons being part of a group or attending an event). The graph is then regularly updated on the basis of new observations and system actions. GraphWOZ is released along with detailed manual annotations related to the user intents, system responses, and reference relations occurring in both user and system turns. Based on GraphWOZ, we present experimental results for two dialogue management tasks, namely conversational entity linking and response ranking. For conversational entity linking, we show how to connect utterance mentions to their corresponding entity in the knowledge graph with a neural model relying on a combination of both string and graph-based features. Response ranking is then performed by summarizing the relevant content of the graph into a text, which is concatenated with the dialogue history and employed as input to score possible responses to a given dialogue state.},
  keywords = {Dialogue Management, Knowledge Graph}
}

