We introduce Efficient LLM Token Extraction (ELTEX), a framework addressing the critical challenge of LLM domain specialization by systematically extracting and integrating domain indicators throughout synthetic data generation. Unlike approaches relying on implicit knowledge transfer, ELTEX explicitly leverages domain signals to maintain specialized knowledge integrity. In our cybersecurity case study, ELTEX-enhanced data enables a fine-tuned Gemma-2B model to achieve performance competitive with GPT-4o on blockchain cyberattack classification while reducing computational requirements. Our Google Sheets implementation makes ELTEX accessible to non-technical users. Our contributions include: (1) the ELTEX framework; (2) Google Sheets Add-on implementation; (3) empirical validation showing how ELTEX bridges performance gaps between small and large models; and (4) a synthetic dataset of 11,448 texts for blockchain cyberattack detection.
Cite
@article{arxiv.2503.15055,
title = {ELTEX: A Framework for Domain-Driven Synthetic Data Generation},
author = {Arina Razmyslovich and Kseniia Murasheva and Sofia Sedlova and Julien Capitaine and Eugene Dmitriev},
journal= {arXiv preprint arXiv:2503.15055},
year = {2025}
}