Ontologies in Design: How Imagining a Tree Reveals Possibilites and Assumptions in Large Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912308192608256 |
|---|---|
| author | Haghighi, Nava Yu, Sunny Landay, James Rosner, Daniela |
| author_facet | Haghighi, Nava Yu, Sunny Landay, James Rosner, Daniela |
| contents | Amid the recent uptake of Generative AI, sociotechnical scholars and critics have traced a multitude of resulting harms, with analyses largely focused on values and axiology (e.g., bias). While value-based analyses are crucial, we argue that ontologies -- concerning what we allow ourselves to think or talk about -- is a vital but under-recognized dimension in analyzing these systems. Proposing a need for a practice-based engagement with ontologies, we offer four orientations for considering ontologies in design: pluralism, groundedness, liveliness, and enactment. We share examples of potentialities that are opened up through these orientations across the entire LLM development pipeline by conducting two ontological analyses: examining the responses of four LLM-based chatbots in a prompting exercise, and analyzing the architecture of an LLM-based agent simulation. We conclude by sharing opportunities and limitations of working with ontologies in the design and development of sociotechnical systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_03029 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ontologies in Design: How Imagining a Tree Reveals Possibilites and Assumptions in Large Language Models Haghighi, Nava Yu, Sunny Landay, James Rosner, Daniela Human-Computer Interaction Computation and Language Amid the recent uptake of Generative AI, sociotechnical scholars and critics have traced a multitude of resulting harms, with analyses largely focused on values and axiology (e.g., bias). While value-based analyses are crucial, we argue that ontologies -- concerning what we allow ourselves to think or talk about -- is a vital but under-recognized dimension in analyzing these systems. Proposing a need for a practice-based engagement with ontologies, we offer four orientations for considering ontologies in design: pluralism, groundedness, liveliness, and enactment. We share examples of potentialities that are opened up through these orientations across the entire LLM development pipeline by conducting two ontological analyses: examining the responses of four LLM-based chatbots in a prompting exercise, and analyzing the architecture of an LLM-based agent simulation. We conclude by sharing opportunities and limitations of working with ontologies in the design and development of sociotechnical systems. |
| title | Ontologies in Design: How Imagining a Tree Reveals Possibilites and Assumptions in Large Language Models |
| topic | Human-Computer Interaction Computation and Language |
| url | https://arxiv.org/abs/2504.03029 |