On the Impact of Requirements Smells in Prompts: The Case of Automated Traceability

Large language models (LLMs) are increasingly used to generate software artifacts, such as source code, tests, and trace links. Requirements play a central role in shaping the input prompts that guide LLMs, as they are often used as part of the prompts to synthesize the artifacts. However, the impac...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE/ACM International Conference on Software Engineering: New Ideas and Emerging Technologies Results (Online) S. 51 - 55
Hauptverfasser: Vogelsang, Andreas, Korn, Alexander, Broccia, Giovanna, Ferrari, Alessio, Fischbach, Jannik, Arora, Chetan
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 27.04.2025
Schlagworte:
ISSN:2832-7632
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Large language models (LLMs) are increasingly used to generate software artifacts, such as source code, tests, and trace links. Requirements play a central role in shaping the input prompts that guide LLMs, as they are often used as part of the prompts to synthesize the artifacts. However, the impact of requirements formulation on LLM performance remains unclear. In this paper, we investigate the role of requirements smells- indicators of potential issues like ambiguity and inconsistency- when used in prompts for LLMs. We conducted experiments using two LLMs focusing on automated trace link generation between requirements and code. Our results show mixed outcomes: while requirements smells had a small but significant effect when predicting whether a requirement was implemented in a piece of code (i.e., a trace link exists), no significant effect was observed when tracing the requirements with the associated lines of code. These findings suggest that requirements smells can affect LLM performance in certain SE tasks but may not uniformly impact all tasks. We highlight the need for further research to understand these nuances and propose future work toward developing guidelines for mitigating the negative effects of requirements smells in AI-driven SE processes.
AbstractList Large language models (LLMs) are increasingly used to generate software artifacts, such as source code, tests, and trace links. Requirements play a central role in shaping the input prompts that guide LLMs, as they are often used as part of the prompts to synthesize the artifacts. However, the impact of requirements formulation on LLM performance remains unclear. In this paper, we investigate the role of requirements smells- indicators of potential issues like ambiguity and inconsistency- when used in prompts for LLMs. We conducted experiments using two LLMs focusing on automated trace link generation between requirements and code. Our results show mixed outcomes: while requirements smells had a small but significant effect when predicting whether a requirement was implemented in a piece of code (i.e., a trace link exists), no significant effect was observed when tracing the requirements with the associated lines of code. These findings suggest that requirements smells can affect LLM performance in certain SE tasks but may not uniformly impact all tasks. We highlight the need for further research to understand these nuances and propose future work toward developing guidelines for mitigating the negative effects of requirements smells in AI-driven SE processes.
Author Broccia, Giovanna
Korn, Alexander
Vogelsang, Andreas
Ferrari, Alessio
Fischbach, Jannik
Arora, Chetan
Author_xml – sequence: 1
  givenname: Andreas
  surname: Vogelsang
  fullname: Vogelsang, Andreas
  email: vogelsang@cs.uni-koeln.de
  organization: University of Cologne,Cologne,Germany
– sequence: 2
  givenname: Alexander
  surname: Korn
  fullname: Korn, Alexander
  email: korn@cs.uni-koeln.de
  organization: University of Cologne,Cologne,Germany
– sequence: 3
  givenname: Giovanna
  surname: Broccia
  fullname: Broccia, Giovanna
  email: giovanna.broccia@isti.cnr.it
  organization: CNR-ISTI,Pisa,Italy
– sequence: 4
  givenname: Alessio
  surname: Ferrari
  fullname: Ferrari, Alessio
  email: alessio.ferrari@ucd.ie
  organization: University College Dublin,Dublin,Ireland
– sequence: 5
  givenname: Jannik
  surname: Fischbach
  fullname: Fischbach, Jannik
  email: jannik.fischbach@netlight.com
  organization: Netlight Consulting GmbH and Fortiss GmbH,Munich,Germany
– sequence: 6
  givenname: Chetan
  surname: Arora
  fullname: Arora, Chetan
  email: chetan.arora@monash.edu
  organization: Monash University,Melbourne,Australia
BookMark eNot0M1OwzAQBGCDQKKUvgEH8wApXju2E25V1EKkiqK2nKvFWYug_JTYPfTtCYLTSKNPc5hbdtX1HTH2AGIOIPLHstgtk9dyuTVGaTmXQuq5EALMBZvlNs-UAq0sAFyyicyUTKxR8obNQvgamZIAFrIJ2206Hj-Jl-0RXeS951v6PtUDtdTFwHctNU3gdcffhr49xvDE96MuMNCvXZxi32Kkiu8HdIQfdVPH8x279tgEmv3nlL2vlvviJVlvnstisU5QWhETEs6CEuC9BpdiJZzXSMJIqvLUp0je5-hTMKh95sxYKl2lVlltyFVUqSm7_9utiehwHOoWh_NhfEeqPAX1A2hbVSE
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICSE-NIER66352.2025.00016
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331537111
EISSN 2832-7632
EndPage 55
ExternalDocumentID 11023941
Genre orig-research
GroupedDBID 6IE
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-a270t-e0c71301ff51c4ad0cf5ae062ed94f4aeff9af416a5f8c6d9435d473756ecded3
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001552151900011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Jun 18 06:01:24 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a270t-e0c71301ff51c4ad0cf5ae062ed94f4aeff9af416a5f8c6d9435d473756ecded3
PageCount 5
ParticipantIDs ieee_primary_11023941
PublicationCentury 2000
PublicationDate 2025-April-27
PublicationDateYYYYMMDD 2025-04-27
PublicationDate_xml – month: 04
  year: 2025
  text: 2025-April-27
  day: 27
PublicationDecade 2020
PublicationTitle IEEE/ACM International Conference on Software Engineering: New Ideas and Emerging Technologies Results (Online)
PublicationTitleAbbrev ICSE-NIER
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211718
Score 2.2966938
Snippet Large language models (LLMs) are increasingly used to generate software artifacts, such as source code, tests, and trace links. Requirements play a central...
SourceID ieee
SourceType Publisher
StartPage 51
SubjectTerms Codes
Focusing
Guidelines
Large language models
LLMs
Requirements Eng
Smells
Software
Software engineering
Source coding
Traceability
Title On the Impact of Requirements Smells in Prompts: The Case of Automated Traceability
URI https://ieeexplore.ieee.org/document/11023941
WOSCitedRecordID wos001552151900011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA46RDypONH5gwhe49I2TVpvMjbcZY5NYbcRk_dgsLVj7QT_e5NsTi8evJXQQHlN-733ku_7CLnnklsvMMkUomHCAjD3FSkmokxjIjODwgSzCTUYZJNJPtyS1QMXBgDC4TN48JdhL9-WZu1bZe0oCk7ertjZV0puyFq7hkriShn3oz0kd1sdzXa_M-6yQb878qjqSVex759wb23-y0klAEnv-J-PcEKaP5Q8OtyBzSnZg-KMjF8K6hI42g9UR1oiHYE_2RtafhUdL2A-r-is8DMXy7p6pG5V0I4DLn_v07ouXb4KljrAMrAR7P5skrde97XzzLYuCUzHitcMuHGFJo8Q08gIbbnBVAOXMdhcoNCAmGt0eZdOMTPSDSapFSpRqQRjwSbnpFGUBVwQKhKMrPTyOSoV5l3kmKVulhauhtNKJZek6SMyXW6EMKbfwWj9MX5FjnzQ_eZLrK5Jo16t4YYcmI96Vq1uw-v7Ap6Pm9c
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwGA2iop5UnPjbCF7j0jZpWm8yNlacdWwTdhsx-QKDrRtrJ_jfm2RzevHgrYQGQtLmfd-XvPcQuqcx1U5gkghjFGEagNi_SBAWJNJEcaIMU95sQuR5Mhym3TVZ3XNhAMBfPoMH9-jP8vVMLV2prB4E3snbJjs7zjqLr-ham5JKZJMZu9Xuobu1kmY9a_SbJM-aPYerjnYVugoKdebmv7xUPJS0Dv85iCNU-yHl4e4Gbo7RFhQnqP9aYBvC4cyTHfHM4B64u72-6Ffi_hQmkxKPC9dzOq_KR2y_C9yw0OXefVpWMxuxgsYWshSsJLs_a-it1Rw02mTtk0BkKGhFgCqbatLAGB4oJjVVhkugcQg6ZYZJMCaVxkZekptExbYx4pqJSPAYlAYdnaLtYlbAGcIsMoGOnYCO4Ey9s9Qk3PaSzGZxUojoHNXcjIzmKymM0fdkXPzRfov224OXzqiT5c-X6MAtgDuKCcUV2q4WS7hGu-qjGpeLG7-UX_IRnyI
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=IEEE%2FACM+International+Conference+on+Software+Engineering%3A+New+Ideas+and+Emerging+Technologies+Results+%28Online%29&rft.atitle=On+the+Impact+of+Requirements+Smells+in+Prompts%3A+The+Case+of+Automated+Traceability&rft.au=Vogelsang%2C+Andreas&rft.au=Korn%2C+Alexander&rft.au=Broccia%2C+Giovanna&rft.au=Ferrari%2C+Alessio&rft.date=2025-04-27&rft.pub=IEEE&rft.eissn=2832-7632&rft.spage=51&rft.epage=55&rft_id=info:doi/10.1109%2FICSE-NIER66352.2025.00016&rft.externalDocID=11023941