Metraipolis › archive › dc_ae34f96269ea
Tasteply: Externalizing Stable and Situational Preference as Manipulable Spatial Objects — arXiv:2611.07851
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07851
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:43:58.384Z
- SHA-256 of the archived text
f52c8277db745622f6026fd7fcde41899b8de0b9540c14f4bbee0d145dceb59c- Stable URL of this page
https://metraipolis.com/documento/dc_ae34f96269ea
How to cite
Tasteply: Externalizing Stable and Situational Preference as Manipulable Spatial Objects — arXiv:2611.07851 — arXiv (en), https://arxiv.org/abs/2611.07851 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ae34f96269ea (Metraipolis archive dc_ae34f96269ea, sha256 f52c8277db745622f6026fd7fcde41899b8de0b9540c14f4bbee0d145dceb59c)
BibTeX
@misc{dcae34f96269ea,
title = {Tasteply: Externalizing Stable and Situational Preference as Manipulable Spatial Objects — arXiv:2611.07851},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07851},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ae34f96269ea; sha256 f52c8277db745622f6026fd7fcde41899b8de0b9540c14f4bbee0d145dceb59c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07851. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Most recommender systems treat user preferences as a single signal to infer and optimize, yet human preferences are a mix of a stable preference and situational preferences that turn on and off depending on context. Through Tasteply, we externalize this preference structure as manipulable spatial objects. Tasteply represents each situational preference as an attractor and the stable preference as an underlying global field. Users can adjust their feed by moving around the space and adjusting the strength of the global field, turning the preference structure that remains latent within the model into something they can see and act on directly to steer the recommendation algorithm. Through an exploratory study (N=5), we found that this spatial control was effective, along with its limits and future direction as a means of manipulating preference-based recommendations. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.HC, nuovi lavori del giorno). Categorie arXiv: Human-Computer Interaction (cs.HC) ; Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2611.07851 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-06T14:21:27.638Z dalla pagina https://arxiv.org/list/cs.HC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).