Exploring LLMs' ability to detect variability in requirements (REFSQ 2024 - Research Track)

Who

Alessandro Fantechi, Stefania Gnesi, Laura Semini, Jill Tamanini

Track

REFSQ 2024 Research Track

Time Zone

The program is currently displayed in (GMT+02:00) Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna.

Use conference time zone: (GMT+02:00) Amsterdam, Berlin, Bern, Rome, Stockholm, ViennaSelect other time zone

The GMT offsets shown reflect the offsets at the moment of the conference.

Time Band

By setting a time band, the program will dim events that are outside this time window. This is useful for (virtual) conferences with a continuous program (with repeated sessions).
The time band will also limit the events that are included in the personal iCalendar subscription service.

Display full programSpecify a time band

Save

When

Tue 9 Apr 2024 11:40 - 12:00 at Vorhangsaal Conference room MA-E0.46 - AI for RE (R2) Chair(s): Fabiano Dalpiaz

Abstract

In this paper, we address the question of whether general-purpose AI-based tools may be useful for detecting variability in Natural Language (NL) requirements documents. For this purpose, we consider GPT-3.5, the Generative Pretrained Transformer language model developed by OpenAI, and Microsoft Bing in creative mode. Using two exemplar NL requirements documents, we compare their variability detection capability with that of experts and that of a rule-based NLP tool.

Alessandro FantechiAuthor

University of Florence

Italy

Stefania GnesiAuthor

Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo"

Italy

Laura SeminiPresenter

Università di Pisa - Dipartimento di Informatica

Italy

Jill TamaniniDiscussant

Fraunhofer IESE

Germany

Time Zone

The program is currently displayed in (GMT+02:00) Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna.

Use conference time zone: (GMT+02:00) Amsterdam, Berlin, Bern, Rome, Stockholm, ViennaSelect other time zone

The GMT offsets shown reflect the offsets at the moment of the conference.

Time Band

Display full programSpecify a time band

Save

Session Program

Tue 9 Apr
Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

11:00 - 12:30	AI for RE (R2)Research Track at Vorhangsaal Conference room MA-E0.46 Chair(s): Fabiano Dalpiaz Utrecht University

11:00 40m Talk		A tertiary study on AI for Requirements EngineeringScientific evaluation Research Track P: Ali Mehraj Tampere University, A: Zheying Zhang Tampere University, A: Kari Systa Tampere University, D: Laura Semini Università di Pisa - Dipartimento di Informatica
11:40 20m Talk		Exploring LLMs' ability to detect variability in requirementsResearch Preview Research Track A: Alessandro Fantechi University of Florence, A: Stefania Gnesi Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo" , P: Laura Semini Università di Pisa - Dipartimento di Informatica, D: Jill Tamanini Fraunhofer IESE
12:00 20m Talk		Opportunities and Limitations of AI in Human-Centered Design - A Research PreviewResearch Preview Research Track A: Anne Hess Technical University of Applied Sciences Würzburg-Schweinfurt / Fraunhofer IESE, A: Thomas Immich Centigrade GmbH, P: Jill Tamanini Fraunhofer IESE, A: Mario Biedenbach Fraunhofer IESE, A: Matthias Koch Fraunhofer IESE, D: Ali Mehraj Tampere University