New publications accepted at Hypertext 2024

The following publications have been accepted at the Hypertext in Poznan, Poland.

Measuring Group Creativity of Dialogic Interaction Systems by Means of Remote Entailment Analysis

Daniel Baumartz, Maxim Konca, Alexander Mehler, Patrick Schrottenbacher and Dominik Braunheim. 2024. Measuring Group Creativity of Dialogic Interaction Systems by Means of Remote Entailment Analysis. Proceedings of the 35th ACM Conference on Hypertext and Social Media. accepted.
BibTeX
@inproceedings{Baumartz:et:al:2024,
  author    = {Baumartz, Daniel and Konca, Maxim and Mehler, Alexander and Schrottenbacher, Patrick
               and Braunheim, Dominik},
  title     = {Measuring Group Creativity of Dialogic Interaction Systems by
               Means of Remote Entailment Analysis},
  year      = {2024},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  booktitle = {Proceedings of the 35th ACM Conference on Hypertext and Social Media},
  keywords  = {VaSiLiLab, virtual hypertext, virtual reality, virtual reality simulation, authoring system},
  location  = {Poznan, Poland},
  series    = {HT '24},
  note      = {accepted}
}


Towards dynamic event handling, environment modification and user feedback in VR-Simulations with the help of Va.Si.Li-Lab

Giuseppe Abrami, Dominik Alexander Wontke, Gurpreet Singh and Alexander Mehler. 2024. Towards dynamic event handling, environment modification and user feedback in VR-Simulations with the help of Va.Si.Li-Lab. Proceedings of the 35th ACM Conference on Hypertext and Social Media. accepted.
BibTeX
@inproceedings{Abrami:et:al:2024:b,
  author    = {Abrami, Giuseppe and Wontke, Dominik Alexander and Singh, Gurpreet
               and Mehler, Alexander},
  title     = {Towards dynamic event handling, environment modification and user
               feedback in VR-Simulations with the help of Va.Si.Li-Lab},
  year      = {2024},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  booktitle = {Proceedings of the 35th ACM Conference on Hypertext and Social Media},
  keywords  = {VaSiLiLab, virtual hypertext, virtual reality, virtual reality simulation, authoring system},
  location  = {Poznan, Poland},
  series    = {HT '24},
  note      = {accepted}
}


HyperCausal: Visualizing Causal Inference in 3D Hypertext

Kevin Bönisch, Manuel Stoeckel and Alexander Mehler. 2024. HyperCausal: Visualizing Causal Inference in 3D Hypertext. Proceedings of the 35th ACM Conference on Hypertext and Social Media. accepted.
BibTeX
@inproceedings{Boenisch:et:al:2024,
  author    = {B\"{o}nisch, Kevin and Stoeckel, Manuel and Mehler, Alexander},
  abstract  = {We present HyperCausal, a 3D hypertext visualization framework
               for exploring causal inference in generative Large Language Models
               (LLMs). HyperCausal maps the generative processes of LLMs into
               spatial hypertexts, where tokens are represented as nodes connected
               by probability-weighted edges. The edges are weighted by the prediction
               scores of next tokens, depending on the underlying language model.
               HyperCausal facilitates navigation through the causal space of
               the underlying LLM, allowing users to explore predicted word sequences
               and their branching. Through comparative analysis of LLM parameters
               such as token probabilities and search algorithms, HyperCausal
               provides insight into model behavior and performance. Implemented
               using the Hugging Face transformers library and Three.js, HyperCausal
               ensures cross-platform accessibility to advance research in natural
               language processing using concepts from hypertext research. We
               demonstrate several use cases of HyperCausal and highlight the
               potential for detecting hallucinations generated by LLMs using
               this framework. The connection with hypertext research arises
               from the fact that HyperCausal relies on user interaction to unfold
               graphs with hierarchically appearing branching alternatives in
               3D space. This approach refers to spatial hypertexts and early
               concepts of hierarchical hypertext structures. A third connection
               concerns hypertext fiction, since the branching alternatives mediated
               by HyperCausal manifest non-linearly organized reading threads
               along artificially generated texts that the user decides to follow
               optionally depending on the reading context.},
  title     = {HyperCausal: Visualizing Causal Inference in 3D Hypertext},
  year      = {2024},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  booktitle = {Proceedings of the 35th ACM Conference on Hypertext and Social Media},
  keywords  = {3D hypertext, large language models, visualization},
  location  = {Poznan, Poland},
  series    = {HT '24},
  note      = {accepted}
}