用15项指标评估生成影像如何丢失口述史中的记忆，发现叙事结构越强越易冲突。
What Gets Lost When Memory Becomes Media? Evaluating AI-Generated Oral History Visualization
- 基于口述史理论设计15项评估指标，聚焦场景构建与叙事保留的冲突
- 82份跨族裔访谈显示，原故事结构越强，生成内容越易出现矛盾
- 提出按叙事强度选系统的路由策略，适合做文化记忆数字化的研究者
当记忆转化为媒体时，什么被遗失了？流散群体的口述史访谈需经历双重转换：第一人称回忆转为第三人称场景，当前访谈空间转为过去的时间与地点。当生成式AI执行此转换时，尚无公认的评估标准。我们从口述史理论推导出成功条件，围绕三种失败模式设计15项指标，对比多智能体场景分解流水线（MAS）与单阶段摘要流水线（SSP）在82份来自流散社区的访谈上的表现，涵盖从原始访谈到六图序列的输出。多数情况下，场景规划与叙事完整性存在冲突，而原始证词的叙事结构强度是该冲突的主要预测因子。本文提出基于失败模式的评估框架、冲突条件的实证分析，并设计依据叙事结构强度进行系统选择的路由协议。
原文摘要 · Abstract (English)
What gets lost when memory becomes media? Diaspora oral-history interviews require a double transformation; first-person recollection to third-person scene, present interview room to past time and place. When generative AI performs this transformation, no agreed criteria for success exist. We derive success conditions from oral-history theory, design 15 metrics around three failure modes, and compare a Multi-Agent Scene-decomposition pipeline (MAS) with a Single Summarization Pipeline (SSP) across 82 interviews from diaspora communities, spanning from oral interviews to 6-image sequences. Scene-planning and narrative preservation conflict in the majority of cases, and the narrative-structure strength of the source testimony is the primary predictor of this conflict. We propose a failure-mode-based evaluation framework, an empirical analysis of conflict conditions, and a routing protocol for system selection based on narrative-structure strength.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。