Trust Dynamics in AI-Assisted Development: Definitions, Factors, and Implications

Software developers increasingly rely on AI code generation utilities. To ensure that "good" code is accepted into the code base and "bad" code is rejected, developers must know when to trust an AI suggestion. Understanding how developers build this intuition is crucial to enhanc...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings / International Conference on Software Engineering S. 1678 - 1690
Hauptverfasser: Sabouri, Sadra, Eibl, Philipp, Zhou, Xinyi, Ziyadi, Morteza, Medvidovic, Nenad, Lindemann, Lars, Chattopadhyay, Souti
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 26.04.2025
Schlagworte:
ISSN:1558-1225
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Software developers increasingly rely on AI code generation utilities. To ensure that "good" code is accepted into the code base and "bad" code is rejected, developers must know when to trust an AI suggestion. Understanding how developers build this intuition is crucial to enhancing developer-AI collaborative programming. In this paper, we seek to understand how developers (1) define and (2) evaluate the trustworthiness of a code suggestion and (3) how trust evolves when using AI code assistants. To answer these questions, we conducted a mixed method study consisting of an in-depth exploratory survey with (n=29) developers followed by an observation study (n=10). We found that comprehensibility and perceived correctness were the most frequently used factors to evaluate code suggestion trustworthiness. However, the gap in developers' definition and evaluation of trust points to a lack of support for evaluating trustworthy code in real-time. We also found that developers often alter their trust decisions, keeping only 52% of original suggestions. Based on these findings, we extracted four guidelines to enhance developer-AI interactions. We validated the guidelines through a survey with (n=7) domain experts and survey members (n=8). We discuss the validated guidelines, how to apply them, and tools to help adopt them.
AbstractList Software developers increasingly rely on AI code generation utilities. To ensure that "good" code is accepted into the code base and "bad" code is rejected, developers must know when to trust an AI suggestion. Understanding how developers build this intuition is crucial to enhancing developer-AI collaborative programming. In this paper, we seek to understand how developers (1) define and (2) evaluate the trustworthiness of a code suggestion and (3) how trust evolves when using AI code assistants. To answer these questions, we conducted a mixed method study consisting of an in-depth exploratory survey with (n=29) developers followed by an observation study (n=10). We found that comprehensibility and perceived correctness were the most frequently used factors to evaluate code suggestion trustworthiness. However, the gap in developers' definition and evaluation of trust points to a lack of support for evaluating trustworthy code in real-time. We also found that developers often alter their trust decisions, keeping only 52% of original suggestions. Based on these findings, we extracted four guidelines to enhance developer-AI interactions. We validated the guidelines through a survey with (n=7) domain experts and survey members (n=8). We discuss the validated guidelines, how to apply them, and tools to help adopt them.
Author Ziyadi, Morteza
Lindemann, Lars
Medvidovic, Nenad
Sabouri, Sadra
Zhou, Xinyi
Eibl, Philipp
Chattopadhyay, Souti
Author_xml – sequence: 1
  givenname: Sadra
  surname: Sabouri
  fullname: Sabouri, Sadra
  email: sabourih@usc.edu
  organization: University of Southern California,Department of Computer Science,Los Angeles,California
– sequence: 2
  givenname: Philipp
  surname: Eibl
  fullname: Eibl, Philipp
  email: eibl@usc.edu
  organization: University of Southern California,Department of Computer Science,Los Angeles,California
– sequence: 3
  givenname: Xinyi
  surname: Zhou
  fullname: Zhou, Xinyi
  email: xzhou141@usc.edu
  organization: University of Southern California,Department of Computer Science,Los Angeles,California
– sequence: 4
  givenname: Morteza
  surname: Ziyadi
  fullname: Ziyadi, Morteza
  email: mziyadi@amazon.com
  organization: Amazon AGI
– sequence: 5
  givenname: Nenad
  surname: Medvidovic
  fullname: Medvidovic, Nenad
  email: neno@usc.edu
  organization: University of Southern California,Department of Computer Science,Los Angeles,California
– sequence: 6
  givenname: Lars
  surname: Lindemann
  fullname: Lindemann, Lars
  email: llindema@usc.edu
  organization: University of Southern California,Department of Computer Science,Los Angeles,California
– sequence: 7
  givenname: Souti
  surname: Chattopadhyay
  fullname: Chattopadhyay, Souti
  email: schattop@usc.edu
  organization: University of Southern California,Department of Computer Science,Los Angeles,California
BookMark eNotkF1LwzAYhaMouM39g130B9iZN9mbNN6VfWhhIOK8Hm_TFCJrWpoo7N871KtzHg48F2fKbkIfHGML4EsAbh6r9fsWUa70UnCBS87BmCs2N9oUUgJyVAau2QQQixyEwDs2jfGTc65WxkzY22H8iinbnAN13sbMh6ys8jJGH5Nrso37dqd-6FxITxdoffDJ9yE-ZDuyqR8vhUKTVd1w8pZ-p3t229Ipuvl_ztjHbntYv-T71-dqXe5zEoqnnGyhlCrAtQIBpGp4oRG1UbK1WpO1Td1SjTXUoDTUCokTETRoZC2hJTljiz-vd84dh9F3NJ6Pl0-EMaKQP2s8UgM
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICSE55347.2025.00199
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISBN 9798331505691
EISSN 1558-1225
EndPage 1690
ExternalDocumentID 11029928
Genre orig-research
GroupedDBID -~X
.4S
.DC
29O
5VS
6IE
6IF
6IH
6IK
6IL
6IM
6IN
8US
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
ARCSS
AVWKF
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
EDO
FEDTE
I-F
IEGSK
IJVOP
IPLJI
M43
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-a260t-ac866681ef251136d087557963fc77accdbfab5b1b1671b65a0aaa1d593b31fa3
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001538318100131&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 01:40:27 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a260t-ac866681ef251136d087557963fc77accdbfab5b1b1671b65a0aaa1d593b31fa3
PageCount 13
ParticipantIDs ieee_primary_11029928
PublicationCentury 2000
PublicationDate 2025-April-26
PublicationDateYYYYMMDD 2025-04-26
PublicationDate_xml – month: 04
  year: 2025
  text: 2025-April-26
  day: 26
PublicationDecade 2020
PublicationTitle Proceedings / International Conference on Software Engineering
PublicationTitleAbbrev ICSE
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0006499
Score 2.3038652
Snippet Software developers increasingly rely on AI code generation utilities. To ensure that "good" code is accepted into the code base and "bad" code is rejected,...
SourceID ieee
SourceType Publisher
StartPage 1678
SubjectTerms AI-code assistants
Artificial intelligence
Codes
Collaboration
Guidelines
Programming
Real-time systems
Software
Software development
Software development management
Software engineering
Surveys
Trust
Title Trust Dynamics in AI-Assisted Development: Definitions, Factors, and Implications
URI https://ieeexplore.ieee.org/document/11029928
WOSCitedRecordID wos001538318100131&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/eLvHCXMwlV07b8IwED4V1KETfVD1LQ8dScFxbCfdKgoqUoWoSis25MdFYgkVhP7-2k6gLB262V4i3cl3-c733Qdwb2NqGSKPDLJelHiOrmY69dUmI6RimQ0qEZ-vcjxOZ7NsUpPVAxcGEUPzGT74ZXjLt0uz8aWyrktVLnrGaQMaUoqKrLULu8L9u9fcONrLuqP--4BzlkiHAWNfNwnjXfcUVEICGbb--eljaP9S8chkl2RO4ACLU2httRhIfTXP4G3qyRPkuRKYX5NFQZ5GkTO-d6Mle71Bj26TL4qqVatDhpXgToeowpLRXn95Gz6Gg2n_JarlEiLlQEkZKZM6LJJSzD1sYML6YfWeaspyI6Uyxupcaa6ppkJSLbjqKaWo5RnTjOaKnUOzWBZ4AcRoxBRTSrUViUSemSSjXBoXHRVzkOQS2t5E869qIsZ8a52rP86v4ch7wb_CxOIGmuVqg7dwaL7LxXp1F_z4A-lsnqw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED5BQYKpPIp444GxoXUcxwkbKq0aUaoiCupW-XGRsqSoD34_dpKWLgxstpdId_JdvvN99wHcG58ahsg9jaztBY6jq5iKXLVJh0Ky2BQqEZ8DMRxGk0k8qsjqBRcGEYvmM3xwy-It38z0ypXKWjZV2ejpR7uw56SzKrrWJvCG9u-9YsfRdtxKOu9dzlkgLAr0XeWkGPC6paFSpJBe_Z8fP4LGLxmPjDZp5hh2MD-B-lqNgVSX8xTexo4-QZ5LifkFyXLylHjW_M6Rhmx1Bz3aTZrlZbNWk_RKyZ0mkbkhyVaHeQM-et1xp-9VggmetLBk6UkdWTQSUUwdcGChcePqHdmUpVoIqbVRqVRcUUVDQVXIZVtKSQ2PmWI0lewMavksx3MgWiFGGFGqTBgI5LEOYsqFtvFRMgtKLqDhTDT9KmdiTNfWufzj_A4O-uPXwXSQDF-u4NB5xL3J-OE11JbzFd7Avv5eZov5beHTH10qofU
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=Proceedings+%2F+International+Conference+on+Software+Engineering&rft.atitle=Trust+Dynamics+in+AI-Assisted+Development%3A+Definitions%2C+Factors%2C+and+Implications&rft.au=Sabouri%2C+Sadra&rft.au=Eibl%2C+Philipp&rft.au=Zhou%2C+Xinyi&rft.au=Ziyadi%2C+Morteza&rft.date=2025-04-26&rft.pub=IEEE&rft.eissn=1558-1225&rft.spage=1678&rft.epage=1690&rft_id=info:doi/10.1109%2FICSE55347.2025.00199&rft.externalDocID=11029928