EUVIMEDDécouvrir EUVIMED
Open access · CC BY 4.0

SCIM: Self-Correcting Iterative Mechanism for Retrieval-Augmented Generation

Ke Li, Tingting Zhang

Electronics · 2026-02-27 · 15 (5) · 996

DOI: 10.3390/electronics15050996 ↗

At a glance

Journal article in Electronics, published online on 2026-02-27. Written by Ke Li and 1 co-authors. Cited 1 times so far (Crossref); 35 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Social Science Foundation of China.

RésuméRéférences bibliographiquesCiteRelated studies

Abstract (original language)

Standard Retrieval-Augmented Generation (RAG) models are limited by their “one-shot” nature, failing to assess or improve answer quality dynamically. To address this, we introduce SCIM (Self-Correcting Iterative Mechanism), a framework featuring multi-dimensional evaluation and adaptive retrieval. A key distinction of SCIM is its efficiency: it operates on a lightweight Flan-T5-base model (250M parameters) and requires no fine-tuning, challenging the industry’s reliance on 7B+ parameter models. Experimental results across four major benchmarks show that SCIM yields a 17.2% improvement over standard RAG (p

Funding

  • National Social Science Foundation of China

Cite

APA

Li, K., & Zhang, T. (2026). SCIM: Self-Correcting Iterative Mechanism for Retrieval-Augmented Generation. Electronics, 15(5), 996. https://doi.org/10.3390/electronics15050996

Vancouver

Li K, Zhang T. SCIM: Self-Correcting Iterative Mechanism for Retrieval-Augmented Generation. Electronics. 2026;15(5):996. doi:10.3390/electronics15050996

BibTeX
@article{Li2026,
  author = {Li, Ke and Zhang, Tingting},
  title = {SCIM: Self-Correcting Iterative Mechanism for Retrieval-Augmented Generation},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {5},
  pages = {996},
  doi = {10.3390/electronics15050996}
}
Start for free →