Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dente, Francesco, Dalpiaz, Fabiano, Papotti, Paolo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.08622
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915543157571584
author Dente, Francesco
Dalpiaz, Fabiano
Papotti, Paolo
author_facet Dente, Francesco
Dalpiaz, Fabiano
Papotti, Paolo
contents Large language models (LLMs) can be employed for automating the generation of software requirements from natural language inputs such as the transcripts of elicitation interviews. However, evaluating whether those derived requirements faithfully reflect the stakeholders' needs remains a largely manual task. We introduce Text2Stories, a task and metrics for text-to-story alignment that allow quantifying the extent to which requirements (in the form of user stories) match the actual needs expressed by the elicitation session participants. Given an interview transcript and a set of user stories, our metric quantifies (i) correctness: the proportion of stories supported by the transcript, and (ii) completeness: the proportion of transcript supported by at least one story. We segment the transcript into text chunks and instantiate the alignment as a matching problem between chunks and stories. Experiments over four datasets show that an LLM-based matcher achieves 0.86 macro-F1 on held-out annotations, while embedding models alone remain behind but enable effective blocking. Finally, we show how our metrics enable the comparison across sets of stories (e.g., human vs. generated), positioning Text2Stories as a scalable, source-faithful complement to existing user-story quality criteria.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08622
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Text2Stories: Evaluating the Alignment Between Stakeholder Interviews and Generated User Stories
Dente, Francesco
Dalpiaz, Fabiano
Papotti, Paolo
Computation and Language
Software Engineering
Large language models (LLMs) can be employed for automating the generation of software requirements from natural language inputs such as the transcripts of elicitation interviews. However, evaluating whether those derived requirements faithfully reflect the stakeholders' needs remains a largely manual task. We introduce Text2Stories, a task and metrics for text-to-story alignment that allow quantifying the extent to which requirements (in the form of user stories) match the actual needs expressed by the elicitation session participants. Given an interview transcript and a set of user stories, our metric quantifies (i) correctness: the proportion of stories supported by the transcript, and (ii) completeness: the proportion of transcript supported by at least one story. We segment the transcript into text chunks and instantiate the alignment as a matching problem between chunks and stories. Experiments over four datasets show that an LLM-based matcher achieves 0.86 macro-F1 on held-out annotations, while embedding models alone remain behind but enable effective blocking. Finally, we show how our metrics enable the comparison across sets of stories (e.g., human vs. generated), positioning Text2Stories as a scalable, source-faithful complement to existing user-story quality criteria.
title Text2Stories: Evaluating the Alignment Between Stakeholder Interviews and Generated User Stories
topic Computation and Language
Software Engineering
url https://arxiv.org/abs/2510.08622