Research Article

Semantic Consensus-Based Multi-LLM Architecture for TÜBİTAK Proposal Generation

Volume: 6 July 7, 2026
TR EN

Semantic Consensus-Based Multi-LLM Architecture for TÜBİTAK Proposal Generation

Abstract

This study proposes a multi-model large language model (LLM)–based framework for the automated generation of high-quality TÜBİTAK project proposals. The primary aim of the study is to improve the consistency, academic quality, and reliability of AI-generated project texts by reducing single-model bias. The scope of the proposed system covers the full structure of TÜBİTAK project applications, including objectives, originality, expected impact, cost estimation, and work planning. Methodologically, the system first generates multiple independent project drafts using different state-of-the-art LLMs under a unified and controlled prompt structure. Each draft is then decomposed into predefined evaluation sections. These sections are embedded using a multilingual sentence-level transformer model, and semantic similarities among corresponding sections are calculated using cosine similarity. For each section, the text with the highest average similarity score is selected as the most representative output, reflecting semantic consensus across models. Confidence scores are also computed to quantify the reliability of the selected content. Experimental results show that the proposed approach produces a coherent, referee-level project proposal with reduced stylistic variation and improved structural consistency. The study concludes that semantic consensus–driven multi-model integration is an effective decision-support mechanism for academic project preparation.

Keywords

References

  1. [1] TÜBİTAK, Araştırma Destek Programları Başkanlığı Proje Değerlendirme Kriterleri, Ankara, Türkiye, 2023.
  2. [2] OECD, Peer Review and Project Evaluation in Public Research Funding, OECD Publishing, Paris, France, 2020.
  3. [3] J. M. Swales and C. B. Feak, Academic Writing for Graduate Students, 3rd ed., Ann Arbor, MI, USA: Univ. Michigan Press, 2012.
  4. [4] T. Brown et al., “Language models are few-shot learners,” in Advances in Neural Information Processing Systems (NeurIPS), 2020, pp. 1877–1901.
  5. [5] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. NAACL-HLT, 2019, pp. 4171–4186.
  6. [6] S. Min, M. Lewis, H. Hajishirzi, and L. Zettlemoyer, “Rethinking the role of demonstrations: What makes in-context learning work?” in Proc. EMNLP, 2022, pp. 11048–11064.
  7. [7] A. Vaswani et al., “Attention is all you need,” in Advances in Neural Information Processing Systems, 2017, pp. 5998–6008.
  8. [8] Y. Liu et al., “RoBERTa: A robustly optimized BERT pretraining approach,” arXiv:1907.11692, 2019. [9] E. M. Bender, T. Gebru, A. McMillan-Major, and S. Shmitchell, “On the dangers of stochastic parrots,” in Proc. ACM FAccT, 2021, pp. 610–623.

Details

Primary Language

English

Subjects

Natural Language Processing

Journal Section

Research Article

Publication Date

July 7, 2026

Submission Date

February 20, 2026

Acceptance Date

June 30, 2026

Published in Issue

Year 2026 Volume: 6

APA
Aktaş, Y., Yiğit, T., Ersoy, M., & Üncü, İ. S. (2026). Semantic Consensus-Based Multi-LLM Architecture for TÜBİTAK Proposal Generation. Advances in Artificial Intelligence Research, 6. https://doi.org/10.54569/aair.1894025
AMA
1.Aktaş Y, Yiğit T, Ersoy M, Üncü İS. Semantic Consensus-Based Multi-LLM Architecture for TÜBİTAK Proposal Generation. Adv. Artif. Intell. Res. 2026;6. doi:10.54569/aair.1894025
Chicago
Aktaş, Yeşim, Tuncay Yiğit, Mevlüt Ersoy, and İsmail Serkan Üncü. 2026. “Semantic Consensus-Based Multi-LLM Architecture for TÜBİTAK Proposal Generation”. Advances in Artificial Intelligence Research 6 (July). https://doi.org/10.54569/aair.1894025.
EndNote
Aktaş Y, Yiğit T, Ersoy M, Üncü İS (July 1, 2026) Semantic Consensus-Based Multi-LLM Architecture for TÜBİTAK Proposal Generation. Advances in Artificial Intelligence Research 6
IEEE
[1]Y. Aktaş, T. Yiğit, M. Ersoy, and İ. S. Üncü, “Semantic Consensus-Based Multi-LLM Architecture for TÜBİTAK Proposal Generation”, Adv. Artif. Intell. Res., vol. 6, July 2026, doi: 10.54569/aair.1894025.
ISNAD
Aktaş, Yeşim - Yiğit, Tuncay - Ersoy, Mevlüt - Üncü, İsmail Serkan. “Semantic Consensus-Based Multi-LLM Architecture for TÜBİTAK Proposal Generation”. Advances in Artificial Intelligence Research 6 (July 1, 2026). https://doi.org/10.54569/aair.1894025.
JAMA
1.Aktaş Y, Yiğit T, Ersoy M, Üncü İS. Semantic Consensus-Based Multi-LLM Architecture for TÜBİTAK Proposal Generation. Adv. Artif. Intell. Res. 2026;6. doi:10.54569/aair.1894025.
MLA
Aktaş, Yeşim, et al. “Semantic Consensus-Based Multi-LLM Architecture for TÜBİTAK Proposal Generation”. Advances in Artificial Intelligence Research, vol. 6, July 2026, doi:10.54569/aair.1894025.
Vancouver
1.Yeşim Aktaş, Tuncay Yiğit, Mevlüt Ersoy, İsmail Serkan Üncü. Semantic Consensus-Based Multi-LLM Architecture for TÜBİTAK Proposal Generation. Adv. Artif. Intell. Res. 2026 Jul. 1;6. doi:10.54569/aair.1894025

88x31.png
Advances in Artificial Intelligence Research is an open access journal which means that the content is freely available without charge to the user or his/her institution. All papers are licensed under a Creative Commons Attribution-NonCommercial 4.0 International License, which allows users to distribute, remix, adapt, and build upon the material in any medium or format for non-commercial purposes only, and only so long as attribution is given to the creator.

Graphic design @ Özden Işıktaş