EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Extracting user profile via large language models and ontologies

Pegah Safari iD, Mehrnoush Shamsfard iD

PLOS One · 11.05.2026 · 21 (5) · e0329934

DOI: 10.1371/journal.pone.0329934 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift PLOS One, online erschienen am 11.05.2026. Verfasst von Pegah Safari und 1 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Computer Science and Engineering, Shahid Beheshti University, Tehran, Iran. Hauptthemen laut MEDLINE: Information Storage and Retrieval, Large Language Models, Natural Language Processing. Die Arbeit nennt 87 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Extracting user-specific profiles that include general personal information, such as hobbies, occupation, or age, is a valuable asset for systems like recommendation engines or personalized chatbots. Currently, most approaches moved toward exploiting the capabilities of large language models (LLMs) on rich languages while less-resourced languages still present significant opportunities for exploration and improvement. In this research, we present a multi-step approach for profile extraction from dialogue systems in Persian as a use case. Through an extensive set of experiments and analyses on various models, we show that LLMs struggle with these languages due to limited language-specific resources and complex linguistic structures. To address this, we propose a hybrid method that combines techniques such as slot filling, in-context learning, and ontology-based inference. Our final results demonstrate a significant improvement over current state-of-the-art models, including LLMs with few-shot examples and even their fine-tuned version. Our method achieves an F-score of 90.46, outperforming GPT-4o and Llama-3-70B by an absolute difference of 17.08 and 24.51 respectively. Our system can also detect inconsistencies in presented information in which our performance substantially exceeds the best performance of GPT-4o and Llama-3-70B with an accuracy of 92%. It is 21% absolutely better than GPT-4o and 47% better than Llama.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Information Storage and RetrievalLarge Language ModelsNatural Language ProcessingHumansLanguageLinguisticsGenerative Artificial IntelligenceDatasets as Topic

Autor:innen und Institutionen

  • Faculty of Computer Science and Engineering, Shahid Beheshti University, Tehran, Iran.

ORCID-Profile: Pegah Safari, Mehrnoush Shamsfard

Zitieren

APA

Safari, P., & Shamsfard, M. (2026). Extracting user profile via large language models and ontologies. PLOS One, 21(5), e0329934. https://doi.org/10.1371/journal.pone.0329934

Vancouver

Safari P, Shamsfard M. Extracting user profile via large language models and ontologies. PLOS One. 2026;21(5):e0329934. doi:10.1371/journal.pone.0329934

BibTeX
@article{Safari2026,
  author = {Safari, Pegah and Shamsfard, Mehrnoush},
  title = {Extracting user profile via large language models and ontologies},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {5},
  pages = {e0329934},
  doi = {10.1371/journal.pone.0329934}
}
Kostenlos starten →