注视感知助手中持久化解释的下游影响
When Interpretations Persist: Downstream Influence in Gaze-Aware Assistants
研究在注视感知流式辅助中固定检索事件、顺序与目标输入，发现自由形式解释会双向放大历史影响：正确历史带来更多有益改动，错误历史带来更多有害改动。对活动或未来行为的无依据、宽泛解释与更大的有害影响相关；证据受限解释保留观察、推断、不确定性与时间范围的区分，减少无依据和过度确定内容，降低错误来源的有害影响，同时保留大部分有益影响。
arXiv:2610.25512v1 Announce Type: new Abstract: AI assistants may carry forward not only observations but also interpretations of what a person is doing or may do next across time. Once retained, these interpretations become context for later predictions and system-triggered outputs. We study whether this representation step changes later behavior in gaze-aware streaming assistance. Holding retrieved events, their order, and the target input fixed, we find that Free-form Interpretation amplifies historical influence in both directions: correct histories produce more helpful changes and wrong histories more harmful changes. Unsupported and broader interpretations about activity or future behavior are associated with greater harmful influence. Evidence-Bounded Interpretation preserves distinctions between observation, inference, uncertainty, and temporal scope, reducing unsupported and overcertain content and lowering wrong-source harmful influence while retaining most helpful influence. The same effect structure appears with a second model. These findings identify persistent interpretation as a consequential design choice for history-aware human-AI systems.
中文翻译还没有生成，先显示原文。
来源：arXiv · Human-Computer Interaction · arxiv.org