Tell Me Your Story: Evaluating Life Writing Generation from Older Adults' Spoken Narratives

ACL ARR 2026 January Submission10201 Authors

Keywords: spoken language understanding, older adults, narrative generation

Abstract: While life writing is essential for preserving memory, its reliance on literacy creates a barrier for many older adults. Our study addresses this by exploring spoken-to-life writing, which transforms oral narratives into written documentation. Although LLMs facilitate automated generation, progress in this field has been hindered by inadequate evaluation methods. To bridge this gap, we introduce an evaluation framework grounded in narrative theory, measuring both Faithfulness (accuracy to the source) and Situatedness (relevance to the audience). Utilizing a benchmark of 402 annotated oral narratives, our study reveals that current LLMs fail to grasp the nuances of spoken discourse and struggle with the discursive gap between older adults and Gen Z, underscoring the need for targeted future research.

Paper Type: Long

Research Area: Speech Processing and Spoken Language Understanding

Research Area Keywords: spoken language understanding

Contribution Types: Model analysis & interpretability, Data resources

Languages Studied: Chinese

Submission Number: 10201