Kevin Bönisch

@inproceedings{Boenisch:et:al:2025,
  title     = {Towards Unified, Dynamic and Annotation-based Visualisations and
               Exploration of Annotated Big Data Corpora with the Help of Unified
               Corpus Explorer},
  author    = {B{\"o}nisch, Kevin and Abrami, Giuseppe and Mehler, Alexander},
  editor    = {Dziri, Nouha and Ren, Sean (Xiang) and Diao, Shizhe},
  booktitle = {Proceedings of the 2025 Conference of the Nations of the Americas
               Chapter of the Association for Computational Linguistics: Human
               Language Technologies (System Demonstrations)},
  year      = {2025},
  address   = {Albuquerque, New Mexico},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2025.naacl-demo.42/},
  pages     = {522--534},
  isbn      = {979-8-89176-191-9},
  abstract  = {The annotation and exploration of large text corpora, both automatic
               and manual, presents significant challenges across multiple disciplines,
               including linguistics, digital humanities, biology, and legal
               science. These challenges are exacerbated by the heterogeneity
               of processing methods, which complicates corpus visualization,
               interaction, and integration. To address these issues, we introduce
               the Unified Corpus Explorer (UCE), a standardized, dockerized,
               open-source and dynamic Natural Language Processing (NLP) application
               designed for flexible and scalable corpus navigation. Herein,
               UCE utilizes the UIMA format for NLP annotations as a standardized
               input, constructing interfaces and features around those annotations
               while dynamically adapting to the corpora and their extracted
               annotations. We evaluate UCE based on a user study and demonstrate
               its versatility as a corpus explorer based on generative AI.},
  note      = {Best Demo Award},
  pdf       = {https://aclanthology.org/2025.naacl-demo.42.pdf}
}

@article{Boenisch:et:al:2025:b,
  author    = {B\"{o}nisch, Kevin and Mehler, Alexander and Babbili, Shaduan
               and Heinrich, Yannick and Stephan, Philipp and Abrami, Giuseppe},
  abstract  = {We present Viki LibraRy, a dynamically built library in virtual
               reality (VR) designed to visualize hypertext systems, with an
               emphasis on collaborative interaction and spatial immersion. Viki
               LibraRy goes beyond traditional methods of text distribution by
               providing a platform where users can share, process, and engage
               with textual information. It operates at the interface of VR,
               collaborative learning and spatial data processing to make reading
               tangible and memorable in a spatially mediated way. The article
               describes the building blocks of Viki LibraRy, its underlying
               architecture, and several use cases. It evaluates Viki LibraRy
               in comparison to a conventional web interface for text retrieval
               and reading. The article shows that Viki LibraRy provides users
               with spatial references for structuring their recall, so that
               they can better remember consulted texts and their meta-information
               (e.g. in terms of subject areas and content categories)},
  title     = {{Viki LibraRy: Collaborative Hypertext Browsing and Navigation
               in Virtual Reality}},
  journal   = {New Review of Hypermedia and Multimedia},
  volume    = {31},
  number    = {1-2},
  pages     = {45--75},
  year      = {2025},
  publisher = {Taylor \& Francis},
  doi       = {10.1080/13614568.2024.2383581},
  url       = {https://doi.org/10.1080/13614568.2024.2383581},
  eprint    = {https://doi.org/10.1080/13614568.2024.2383581}
}

@inbook{Mehler:et:al:2024:a,
  author    = {Mehler, Alexander and Bagci, Mevl{\"u}t and Schrottenbacher, Patrick
               and Henlein, Alexander and Konca, Maxim and Abrami, Giuseppe and B{\"o}nisch, Kevin
               and Stoeckel, Manuel and Spiekermann, Christian and Engel, Juliane},
  editor    = {Zlatkin-Troitschanskaia, Olga and Nagel, Marie-Theres and Klose, Verena
               and Mehler, Alexander},
  title     = {Towards New Data Spaces for the Study of Multiple Documents with
               Va.Si.Li-Lab: A Conceptual Analysis},
  booktitle = {Students', Graduates' and Young Professionals' Critical Use of
               Online Information: Digital Performance Assessment and Training
               within and across Domains},
  year      = {2024},
  publisher = {Springer Nature Switzerland},
  address   = {Cham},
  pages     = {259--303},
  abstract  = {The constitution of multiple documents has so far been studied
               essentially as a process in which a single learner consults a
               number (of segments) of different documents in the context of
               the task at hand in order to construct a mental model for the
               purpose of completing the task. As a result of this research focus,
               the constitution of multiple documents appears predominantly as
               a monomodal, non-interactive process in which mainly textual units
               are studied, supplemented by images, text-image relations and
               comparable artifacts. This approach is reflected in the contextual
               fixity of the research design, in which the learners under study
               search for information using suitably equipped computers. If,
               on the other hand, we consider the openness of multi-agent learning
               situations, this scenario lacks the aspects of interactivity,
               contextual openness and, above all, the multimodality of information
               objects, information processing and information exchange. This
               is where the chapter comes in. It describes Va.Si.Li-Lab as an
               instrument for multimodal measurement for studying and modeling
               multiple documents in the context of interactive learning in a
               multi-agent environment. To this end, the chapter places Va.Si.Li-Lab
               in the spectrum of evolutionary approaches that vary the combination
               of human and machine innovation and selection. It also combines
               the requirements of multimodal representational learning with
               various aspects of contextual plasticity to prepare Va.Si.Li-Lab
               as a system that can be used for experimental research. The chapter
               is conceptual in nature, designing a system of requirements using
               the example of Va.Si.Li-Lab to outline an experimental environment
               in which the study of Critical Online Reasoning (COR) as a group
               process becomes possible. Although the chapter illustrates some
               of these requirements with realistic data from the field of simulation-based
               learning, the focus is still conceptual rather than experimental,
               hypothesis-driven. That is, the chapter is concerned with the
               design of a technology for future research into COR processes.},
  isbn      = {978-3-031-69510-0},
  doi       = {10.1007/978-3-031-69510-0_12},
  url       = {https://doi.org/10.1007/978-3-031-69510-0_12}
}

@inproceedings{Boenisch:Mehler:2024,
  title     = {Finding Needles in Emb(a)dding Haystacks: Legal Document Retrieval
               via Bagging and SVR Ensembles},
  author    = {B\"{o}nisch, Kevin and Mehler, Alexander},
  year      = {2024},
  booktitle = {Proceedings of the 2nd Legal Information Retrieval meets Artificial
               Intelligence Workshop LIRAI 2024},
  location  = {Poznan, Poland},
  publisher = {CEUR-WS.org},
  address   = {Aachen, Germany},
  series    = {CEUR Workshop Proceedings},
  abstract  = {We introduce a retrieval approach leveraging Support Vector Regression
               (SVR) ensembles, bootstrap aggregation (bagging), and embedding
               spaces on the German Dataset for Legal Information Retrieval (GerDaLIR).
               By conceptualizing the retrieval task in terms of multiple binary
               needle-in-a-haystack subtasks, we show improved recall over the
               baselines (0.849 > 0.803 | 0.829) using our voting ensemble, suggesting
               promising initial results, without training or fine-tuning any
               deep learning models. Our approach holds potential for further
               enhancement, particularly through refining the encoding models
               and optimizing hyperparameters.},
  archiveprefix = {arXiv},
  eprint    = {2501.05018},
  url       = {https://arxiv.org/pdf/2501.05018},
  keywords  = {legal information retrieval, support vector regression, word embeddings, bagging ensemble}
}

@inproceedings{Boenisch:et:al:2024,
  author    = {B\"{o}nisch, Kevin and Stoeckel, Manuel and Mehler, Alexander},
  title     = {HyperCausal: Visualizing Causal Inference in 3D Hypertext},
  year      = {2024},
  isbn      = {9798400705953},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  url       = {https://doi.org/10.1145/3648188.3677049},
  doi       = {10.1145/3648188.3677049},
  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.},
  booktitle = {Proceedings of the 35th ACM Conference on Hypertext and Social Media},
  pages     = {330–-336},
  numpages  = {7},
  keywords  = {3D hypertext, large language models, visualization},
  location  = {Poznan, Poland},
  series    = {HT '24},
  video     = {https://www.youtube.com/watch?v=ANHFTupnKhI}
}

@bathesis{boenisch:2023,
  author    = {Kevin B{\"o}nisch},
  title     = {Dialog generation using language models},
  institution = {Goethe University},
  pages     = {28},
  year      = {2023},
  url       = {https://publikationen.ub.uni-frankfurt.de/opus4/frontdoor/index/index/docId/79165},
  repository = {https://github.com/texttechnologylab/ROBERT}
}

@inproceedings{Boenisch:et:al:2023,
  title     = {{Bundestags-Mine}: Natural Language Processing for Extracting
               Key Information from Government Documents},
  isbn      = {9781643684734},
  issn      = {1879-8314},
  url       = {http://dx.doi.org/10.3233/FAIA230996},
  doi       = {10.3233/faia230996},
  booktitle = {Legal Knowledge and Information Systems},
  publisher = {IOS Press},
  author    = {B\"{o}nisch, Kevin and Abrami, Giuseppe and Wehnert, Sabine and Mehler, Alexander},
  year      = {2023}
}

@inproceedings{Babbili:et:al:2023,
  author    = {Babbili, Shaduan and B\"{o}nisch, Kevin and Heinrich, Yannick
               and Stephan, Philipp and Abrami, Giuseppe and Mehler, Alexander},
  title     = {Viki LibraRy: A Virtual Reality Library for Collaborative Browsing
               and Navigation through Hypertext},
  year      = {2023},
  isbn      = {9798400702327},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  url       = {https://doi.org/10.1145/3603163.3609079},
  doi       = {10.1145/3603163.3609079},
  abstract  = {We present Viki LibraRy, a virtual-reality-based system for generating
               and exploring online information as a spatial hypertext. It creates
               a virtual library based on Wikipedia in which Rooms are used to
               make data available via a RESTful backend. In these Rooms, users
               can browse through all articles of the corresponding Wikipedia
               category in the form of Books. In addition, users can access different
               Rooms, through virtual portals. Beyond that, the explorations
               can be done alone or collaboratively, using Ubiq.},
  booktitle = {Proceedings of the 34th ACM Conference on Hypertext and Social Media},
  articleno = {6},
  numpages  = {3},
  keywords  = {virtual reality simulation, virtual reality, virtual hypertext, virtual museum},
  location  = {Rome, Italy},
  series    = {HT '23},
  pdf       = {https://dl.acm.org/doi/pdf/10.1145/3603163.3609079}
}