← 研踪 PaperTrailarXiv:2611.07851 · v1
Tasteply: Externalizing Stable and Situational Preference as Manipulable Spatial Objects
首次提交 2026-11-05 19:30
版本更新 2026-11-05 19:30
雷达观测 2026-11-06 11:06
摘要
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.
期刊信息：UIST 2026 Posters
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-05 19:30 · 最新观测版本
Tasteply: Externalizing Stable and Situational Preference as Manipulable Spatial Objects
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.
查看此版本解读 →查看此版本原文 ↗