Umeå universitets logga

umu.sePublikationer
Ändra sökning
Länk till posten
Permanent länk

Direktlänk
Alaie, Parisima
Publikationer (1 of 1) Visa alla publikationer
Alaie, P., Vallgren, E. & Sandberg, J. (2026). Ground truth heterogeneity: exploring development and non-clinical use of retrieval-augmented generation chatbot in healthcare. In: ECIS 2026 Proceedings: . Paper presented at Thirty-Fourth European Conference on Information Systems (ECIS 2026), June 15-17, 2026, Milan, Italy. Association for Information Systems
Öppna denna publikation i ny flik eller fönster >>Ground truth heterogeneity: exploring development and non-clinical use of retrieval-augmented generation chatbot in healthcare
2026 (Engelska)Ingår i: ECIS 2026 Proceedings, Association for Information Systems, 2026Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Retrieval-augmented generation (RAG) architecture enhances large language models (LLMs) by incorporating external, domain-specific data sources, thereby reducing hallucinations and improving response accuracy. This approach departs from purely generative systems and offers a scalable, cost-efficient alternative for enhancing LLMs. However, the construction of ground truth to enable evolvability (ability to integrate new data continuously) and adaptability (ability to adjust responses to user context and intents dynamically) remains challenging. This study investigates how the challenges of establishing ground truth manifest at the organizational, unit, team, and individual levels within a countywide Swedish healthcare organization. Our analysis reveals that the main challenges stem from the heterogeneity of knowledge practices, which complicate the creation of reliable retrieval from the knowledge base. Furthermore, we identify a trade-off between attempts to enhance accuracy and maintain contextual relevance. These findings contribute practical insights into the micro-foundations of evolvability and adaptability in RAG-based chatbot development.

Ort, förlag, år, upplaga, sidor
Association for Information Systems, 2026
Serie
ECIS 2026 Proceedings, E-ISSN 2184-1934 ; 16
Nyckelord
Retrieval-Augmented Generation, Ground Truth, Generative Artificial Intelligence, Knowledge Heterogeneity, Chatbot.
Nationell ämneskategori
Systemvetenskap, informationssystem och informatik
Identifikatorer
urn:nbn:se:umu:diva-255398 (URN)
Konferens
Thirty-Fourth European Conference on Information Systems (ECIS 2026), June 15-17, 2026, Milan, Italy
Tillgänglig från: 2026-06-22 Skapad: 2026-06-22 Senast uppdaterad: 2026-06-23Bibliografiskt granskad
Organisationer

Sök vidare i DiVA

Visa alla publikationer