Dalarna University's logo and link to the university's website

du.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A Formal Approach to LLM Hallucination Detection and Mitigation
Dalarna University, School of Information and Engineering, Computing. School of Software and IoT Engineering, Jiangxi University of Finance and Economics, Nanchang, China.ORCID iD: 0000-0003-3681-8173
2026 (English)In: 2026 11th International Conference on Cloud Computing and Big Data Analytics (ICCCBDA), Institute of Electrical and Electronics Engineers Inc. , 2026, p. 678-685Conference paper, Published paper (Refereed)
Abstract [en]

This study focuses on 'LLM hallucinations'-a core risk in real-world multi-team projects-and provides its definition, classification, formalized description, as well as an initial approach to mitigation of LLM hallucinations. Through experiments, we demonstrate that hallucinations are an inherent deficit of language models which tend to 'over-complete' the users' requirements and can be effectively mitigated by using structured instructions combined with systematic reviews. This research provides usable theoretical frameworks and practical methodologies for improving the factual reliability of LLM-generated content in project-oriented scenarios. © 2026 IEEE.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc. , 2026. p. 678-685
Keywords [en]
Formal Definition, Hallucination, LLMs, Mitigation Strategy, Formal approach, Formalized description, Language model, LLM, Over-complete, Real-world, Team projects, Formal methods
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:du-55036DOI: 10.1109/ICCCBDA69573.2026.11676510Scopus ID: 2-s2.0-105051520375ISBN: 9798331550264 (electronic)OAI: oai:DiVA.org:du-55036DiVA, id: diva2:2111913
Conference
11th International Conference on Cloud Computing and Big Data Analytics, ICCCBDA 2026, Chengdu, China, 24-26 April 2026
Available from: 2026-10-21 Created: 2026-10-21 Last updated: 2026-10-21Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopushttps://www.scopus.com/pages/publications/105051520375?origin=resultslist

Authority records

Song, William Wei

Search in DiVA

By author/editor
Song, William Wei
By organisation
Computing
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 36 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf