当记忆成为媒介时会失去什么?评估人工智能生成的口述历史可视化
What Gets Lost When Memory Becomes Media? Evaluating AI-Generated Oral History Visualization
浏览论文内容
中文总结 AI 辅助
研究散居海外者口述历史可视化中记忆变媒介时的问题,基于口述历史理论设计指标,比较两种管道,发现场景规划与叙事保留冲突,提出基于失败模式的评估框架、冲突分析及系统选择路由协议。
中文摘要 AI 辅助
当记忆成为媒介时会失去什么?散居海外者的口述历史访谈需要双重转变:从第一人称回忆到第三人称场景,从当前访谈室到过去的时间和地点。当生成式人工智能进行这种转变时,不存在公认的成功标准。我们从口述历史理论中得出成功条件,围绕三种失败模式设计了15个指标,并在来自散居社区的82次访谈中,将多智能体场景分解管道(MAS)与单摘要管道(SSP)进行比较,范围从口述访谈到6图像序列。在大多数情况下,场景规划和叙事保留存在冲突,源证词的叙事结构强度是这种冲突的主要预测因素。我们提出了一个基于失败模式的评估框架、冲突条件的实证分析以及基于叙事结构强度的系统选择路由协议。
英文摘要
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.
发表机构
- AA LAB(AA实验室)
- MODULABS
- Aiffel(艾菲尔公司)
机构由 AI 辅助整理,请以论文原文为准。