EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

"Call My Big Sibling (CMBS)" – A Confidence-Based Strategy Leveraging Instance Selection to Combine Small and Large Language Models for Cost-Effective Text Classification

Claudio Moisés Valiense de Andrade, Washington Cunha, Davi Reis, Celso França, Wasterman Ávila Apolinário, Luana de Castro Santos, Adriana Silvina Pagano, Leonardo Chaves Dutra da Rocha, Marcos André Gonçalves

Journal of the Brazilian Computer Society · 05.05.2026 · 32 (1) · 1233-1249

DOI: 10.5753/jbcs.2026.6153 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Brazilian Computer Society, online erschienen am 05.05.2026. Verfasst von Claudio Moisés Valiense de Andrade und 8 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Transformers have achieved state-of-the-art results, with Large Language Models (LLMs) leading many NLP tasks. However, it remains unclear whether LLMs always outperform first-generation Transformers (aka Small Language Models, SLMs) across different text classification tasks and scenarios (e.g., movie reviews, topic classification). This study compares four SLMs (BERT, RoBERTa, Qwen, BART) with four open LLMs (LLaMA 3.1, Mistral, Falcon, DeepSeek) across nine sentiment and four topic classification datasets, totaling over 1000 results. Results show that open LLMs only moderately outperform or tie with SLMs when fine-tuned, and at a very high computational cost. To address this trade-off, we propose “Call My Big Sibling” (CMBS), a novel confidence-based framework that integrates calibrated SLMs and open LLMs using advanced instance selection techniques. CMBS assigns high-confidence instances to the cheaper SLM, while low-confidence instances are routed to an LLM in zero-shot, in-context, or partially tuned modes, optimizing cost-effectiveness. Experiments show CMBS significantly outperforms SLMs and delivers LLM-level performance at a fraction of the cost, offering a cost-sensitive solution for NLP applications.

Zitieren

APA

Andrade, C. M. V. D., Cunha, W., Reis, D., França, C., Apolinário, W. Á., Santos, L. D. C., Pagano, A. S., Rocha, L. C. D. D., & Gonçalves, M. A. (2026). "Call My Big Sibling (CMBS)" – A Confidence-Based Strategy Leveraging Instance Selection to Combine Small and Large Language Models for Cost-Effective Text Classification. Journal of the Brazilian Computer Society, 32(1), 1233-1249. https://doi.org/10.5753/jbcs.2026.6153

Vancouver

Andrade CMVD, Cunha W, Reis D, França C, Apolinário WÁ, Santos LDC, et al. "Call My Big Sibling (CMBS)" – A Confidence-Based Strategy Leveraging Instance Selection to Combine Small and Large Language Models for Cost-Effective Text Classification. Journal of the Brazilian Computer Society. 2026;32(1):1233-1249. doi:10.5753/jbcs.2026.6153

BibTeX
@article{Andrade2026,
  author = {Andrade, Claudio Moisés Valiense de and Cunha, Washington and Reis, Davi and França, Celso and Apolinário, Wasterman Ávila and Santos, Luana de Castro and Pagano, Adriana Silvina and Rocha, Leonardo Chaves Dutra da and Gonçalves, Marcos André},
  title = {"Call My Big Sibling (CMBS)" – A Confidence-Based Strategy Leveraging Instance Selection to Combine Small and Large Language Models for Cost-Effective Text Classification},
  journal = {Journal of the Brazilian Computer Society},
  year = {2026},
  volume = {32},
  number = {1},
  pages = {1233--1249},
  doi = {10.5753/jbcs.2026.6153}
}
Kostenlos starten →