论文进阶

Trustworthiness

可信度（trustworthiness）：HCI/AI 语境中指 AI 系统本身具备的可靠性、稳健性、公平性等多维属性，属于系统侧特征；在 HCI 文献中严格区别于用户侧的 trust（信任态度）和 reliance（依赖行为）。

English Definition

"In HCI/AI contexts, a multidimensional property of an AI system describing its actual reliability, robustness, fairness, and integrity — a system-side attribute formally distinguished from the user's trust (attitude) and reliance (behavior)."

用法说明 · 针对中文母语者

中文常被直译为'可信赖性'或'信任度'，与 trust 混用。HCI/AI 写作中三者必须区分：trustworthiness 是系统属性（可被测量、评估），trust 是用户心理状态。

常见错误

·与 trust 不加区分地互换使用
·中文译为'信任度'或'可信'，丢失了'系统客观属性'这层含义

真实用例 · 3 条

"trust captures users' attitudes toward relying on model outputs under uncertainty, distinct from reliance (behavior) and trustworthiness (system quality)."

论文Pipeline extracted — review needed·2.1 节中给出 trust 三元定义，明确把 trustworthiness 框定为 system quality

"Huang et al. [22] establishes a benchmark for trustworthiness, emphasizing that it is multi-dimensional, involving not only accuracy but also robustness and fairness."

论文Pipeline extracted — review needed·2.2 节引用 LLM 摘要可信度基准研究，强调 trustworthiness 的多维性

"RQ2 ... affect participants' perceptions of information quality and trustworthiness?"

论文Pipeline extracted — review needed·研究问题中将 quality 与 trustworthiness 并列为结果变量

由 pipeline 自动采集，待人工 review