从叙事文本的任务边界到结构锚定、不确定性触发与交叉校准
From the Task Boundaries of Narrative Text to Structural Anchoring, Uncertainty Triggers, and Cross-Calibration
- Sun Yat-sen University（中山大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出CoNS-Explorer框架，通过实验和访谈揭示用户如何结合因果图、直接解释与故事进行推理，并构建了结构锚定、不确定性触发、解释路由和交叉校准的过程框架及四项设计命题。
AI中文摘要：
因果图表示变量之间的结构关系，但用户仍必须结合当前任务来解读方向、机制和调整条件。以往研究通常将解释格式作为固定条件进行比较，较少关注用户如何在图、直接解释和故事之间分配推理。我们开发了CoNS-Explorer，它利用经过审阅的教学性DAG/SCM来维护共享的因果事实账本，并生成与事实匹配的直接解释和情境化故事。一项受控调查实验（N=240）将两种文本作为完整的呈现包进行比较。在主要GLMM中，故事条件与准确性呈正相关但不确定（OR=1.55，95% CI [0.34,7.10]，p=.572）；群体平均GEE显示显著正效应（OR=1.89，95% CI [1.02,3.48]，p=.042）。任务类型交互将最明显的优势定位于总效应调整。故事还显著提高了情境临场感。在另一项系统任务和访谈研究（N=24）中，参与者在三个因果模型中自由使用图、直接解释和故事。他们通过图和数值结果建立结构锚点，在方向不明确、机制不熟悉或多条路径竞争时查阅文本，并对照其他表示或外部证据检查其判断。综合两项研究，我们提出了一个包含结构锚定、不确定性触发、解释路由和交叉校准的过程框架，以及四项可测试的自适应因果解释设计命题。
英文摘要：
Causal graphs represent structural relationships among variables, yet users must still interpret direction, mechanism, and adjustment conditions in relation to the task at hand. Prior work often compares explanation formats as fixed conditions and pays less attention to how users distribute reasoning across graphs, direct explanations, and stories. We developed CoNS-Explorer, which uses reviewed instructional DAGs/SCMs to maintain a shared causal-fact ledger and generate fact-matched direct explanations and contextualized stories. A controlled survey experiment ($N=240$) compared the two texts as complete presentation packages. In the primary GLMM, the Story condition had a positive but uncertain overall association with accuracy (OR $=1.55$, 95\% CI $[0.34,7.10]$, $p=.572$); a population-averaged GEE showed a significant positive effect (OR $=1.89$, 95\% CI $[1.02,3.48]$, $p=.042$). Task-type interactions localized the clearest advantage to total-effect adjustment. Story also significantly increased situational presence. In a separate system-task and interview study ($N=24$), participants freely used graphs, direct explanations, and stories across three causal models. They established structural anchors with graphs and numerical results, consulted text when direction was unclear, mechanisms were unfamiliar, or multiple paths competed, and checked their judgments against other representations or external evidence. Integrating the two studies, we develop a process framework of structural anchoring, uncertainty triggering, explanation routing, and cross-calibration, together with four testable design propositions for adaptive causal explanation.
