Generative language models potential for requirement engineering applications: insights into current strengths and limitations

Abstract Traditional language models have been extensively evaluated for software engineering domain, however the potential of ChatGPT and Gemini have not been fully explored. To fulfill this gap, the paper in hand presents a comprehensive case study to investigate the potential of both language mod...

Full description

Saved in:
Bibliographic Details
Main Authors: Summra Saleem, Muhammad Nabeel Asim, Ludger Van Elst, Andreas Dengel
Format: Article
Language:English
Published: Springer 2025-05-01
Series:Complex & Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1007/s40747-024-01707-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850273200855842816
author Summra Saleem
Muhammad Nabeel Asim
Ludger Van Elst
Andreas Dengel
author_facet Summra Saleem
Muhammad Nabeel Asim
Ludger Van Elst
Andreas Dengel
author_sort Summra Saleem
collection DOAJ
description Abstract Traditional language models have been extensively evaluated for software engineering domain, however the potential of ChatGPT and Gemini have not been fully explored. To fulfill this gap, the paper in hand presents a comprehensive case study to investigate the potential of both language models for development of diverse types of requirement engineering applications. It deeply explores impact of varying levels of expert knowledge prompts on the prediction accuracies of both language models. Across 4 different public benchmark datasets of requirement engineering tasks, it compares performance of both language models with existing task specific machine/deep learning predictors and traditional language models. Specifically, the paper utilizes 4 benchmark datasets; Pure (7445 samples, requirements extraction), PROMISE (622 samples, requirements classification), REQuestA (300 question answer (QA) pairs) and Aerospace datasets (6347 words, requirements NER tagging). Our experiments reveal that, in comparison to ChatGPT, Gemini requires more careful prompt engineering to provide accurate predictions. Moreover, across requirement extraction benchmark dataset the state-of-the-art F1-score is 0.86 while ChatGPT and Gemini achieved 0.76 and 0.77, respectively. The State-of-the-art F1-score on requirements classification dataset is 0.96 and both language models 0.78. In name entity recognition (NER) task the state-of-the-art F1-score is 0.92 and ChatGPT managed to produce 0.36, and Gemini 0.25. Similarly, across question answering dataset the state-of-the-art F1-score is 0.90 and ChatGPT and Gemini managed to produce 0.91 and 0.88 respectively. Our experiments show that Gemini requires more precise prompt engineering than ChatGPT. Except for question-answering, both models under-perform compared to current state-of-the-art predictors across other tasks.
format Article
id doaj-art-7bc5dc50f7e842988ce217f9d9bfa24d
institution OA Journals
issn 2199-4536
2198-6053
language English
publishDate 2025-05-01
publisher Springer
record_format Article
series Complex & Intelligent Systems
spelling doaj-art-7bc5dc50f7e842988ce217f9d9bfa24d2025-08-20T01:51:35ZengSpringerComplex & Intelligent Systems2199-45362198-60532025-05-0111612210.1007/s40747-024-01707-6Generative language models potential for requirement engineering applications: insights into current strengths and limitationsSummra Saleem0Muhammad Nabeel Asim1Ludger Van Elst2Andreas Dengel3Department of Computer Science, Rhineland-Palatinte Technical University of Kaiserslautern-LandauGerman Research Center for Artificial Intelligence GmbHGerman Research Center for Artificial Intelligence GmbHDepartment of Computer Science, Rhineland-Palatinte Technical University of Kaiserslautern-LandauAbstract Traditional language models have been extensively evaluated for software engineering domain, however the potential of ChatGPT and Gemini have not been fully explored. To fulfill this gap, the paper in hand presents a comprehensive case study to investigate the potential of both language models for development of diverse types of requirement engineering applications. It deeply explores impact of varying levels of expert knowledge prompts on the prediction accuracies of both language models. Across 4 different public benchmark datasets of requirement engineering tasks, it compares performance of both language models with existing task specific machine/deep learning predictors and traditional language models. Specifically, the paper utilizes 4 benchmark datasets; Pure (7445 samples, requirements extraction), PROMISE (622 samples, requirements classification), REQuestA (300 question answer (QA) pairs) and Aerospace datasets (6347 words, requirements NER tagging). Our experiments reveal that, in comparison to ChatGPT, Gemini requires more careful prompt engineering to provide accurate predictions. Moreover, across requirement extraction benchmark dataset the state-of-the-art F1-score is 0.86 while ChatGPT and Gemini achieved 0.76 and 0.77, respectively. The State-of-the-art F1-score on requirements classification dataset is 0.96 and both language models 0.78. In name entity recognition (NER) task the state-of-the-art F1-score is 0.92 and ChatGPT managed to produce 0.36, and Gemini 0.25. Similarly, across question answering dataset the state-of-the-art F1-score is 0.90 and ChatGPT and Gemini managed to produce 0.91 and 0.88 respectively. Our experiments show that Gemini requires more precise prompt engineering than ChatGPT. Except for question-answering, both models under-perform compared to current state-of-the-art predictors across other tasks.https://doi.org/10.1007/s40747-024-01707-6Requirement engineeringRequirements extractionRequirements classificationNamed entity recognitionQuestion answering systemGenerative language models
spellingShingle Summra Saleem
Muhammad Nabeel Asim
Ludger Van Elst
Andreas Dengel
Generative language models potential for requirement engineering applications: insights into current strengths and limitations
Complex & Intelligent Systems
Requirement engineering
Requirements extraction
Requirements classification
Named entity recognition
Question answering system
Generative language models
title Generative language models potential for requirement engineering applications: insights into current strengths and limitations
title_full Generative language models potential for requirement engineering applications: insights into current strengths and limitations
title_fullStr Generative language models potential for requirement engineering applications: insights into current strengths and limitations
title_full_unstemmed Generative language models potential for requirement engineering applications: insights into current strengths and limitations
title_short Generative language models potential for requirement engineering applications: insights into current strengths and limitations
title_sort generative language models potential for requirement engineering applications insights into current strengths and limitations
topic Requirement engineering
Requirements extraction
Requirements classification
Named entity recognition
Question answering system
Generative language models
url https://doi.org/10.1007/s40747-024-01707-6
work_keys_str_mv AT summrasaleem generativelanguagemodelspotentialforrequirementengineeringapplicationsinsightsintocurrentstrengthsandlimitations
AT muhammadnabeelasim generativelanguagemodelspotentialforrequirementengineeringapplicationsinsightsintocurrentstrengthsandlimitations
AT ludgervanelst generativelanguagemodelspotentialforrequirementengineeringapplicationsinsightsintocurrentstrengthsandlimitations
AT andreasdengel generativelanguagemodelspotentialforrequirementengineeringapplicationsinsightsintocurrentstrengthsandlimitations