arXiv cs.AI· Zhiyu An, Ziyi Xuan, Yu Yang, Wan Du·· 3 天前AI 评分18
不确定性估计如何提升主动式智能助手对齐：一篇愿景论文
Vision: "What Don't I Know About User's Preferences?" How Uncertainty Estimation Improves Proactive Assistant Alignment
AI 导读
这篇愿景论文提出，不确定性估计能为主动式智能助手补上偏好预测所缺失的信息，即助手对预测偏好概率有多确定、置信来自群体假设还是个人数据、歧义源于用户偏好本身多变还是特定情境数据不足。作者以家庭助手为例，并借鉴人类轨迹预测、个性化活动识别、信息收集与基于模型的控制等邻近领域经验，展望不确定性感知的主动式助手如何应对主动交互中的关键挑战。
正文 · 原文
Abstract:Proactive Smart Assistants (PSAs) increasingly use general knowledge, learned patterns from group-level data, patterns from individual user's data, and recent sensor observations to anticipate which action a user may prefer. Existing systems typically select actions from predicted user preference likelihoods, but these likelihoods alone do not reveal how reliable the prediction is, which evidence supports it, or why ambiguity remains. In this vision paper, we argue that uncertainty estimation can provide this missing information and substantially change appropriate downstream behavior. Using the example of a home assistant, we introduce the questions that uncertainty estimation aims to answer, i.e. how sure is the assistant about the predicted preference likelihood, whether the confidence come from group-level assumptions or individual's data, and whether likelihood ambiguity reflect the user's intrinsic preference variability or insufficient data for the particular situation. We further introduce uncertainty estimation applications in neighboring domains, such as human trajectory prediction, personalized activity recognition, information-collection, and model-based control. Finally, we draw on insights from neighboring domains to envision how future uncertainty-aware proactive assistants may address key challenges in proactive interaction.
| Comments: | Published in Companion of the 2026 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp Companion '26) PEACE Workshop |
| Subjects: | Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2610.15948 [cs.AI] |
| (or arXiv:2610.15948v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.15948 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | Companion of the 2026 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp Companion '26) |
| Related DOI: | https://doi.org/10.1145/3798063.3839206
DOI(s) linking to related resources |
Submission history
From: Zhiyu An [view email]
[v1]
Sun, 11 Oct 2026 22:13:37 UTC (2,088 KB)
来源：arXiv cs.AI · arxiv.org