@inproceedings{smits-walkowiak-2026-evaluating,
    title = "Evaluating Cost-Efficiency of {LLM}s in a {RAG} Setup on {P}olish {W}ikipedia: Quality vs. Energy Consumption",
    author = "Smits, Patrycja  and
      Walkowiak, Tomasz",
    editor = "Baez Santamaria, Selene  and
      Somayajula, Sai Ashish  and
      Yamaguchi, Atsuki",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 4: Student Research Workshop)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-srw.55/",
    pages = "747--759",
    ISBN = "979-8-89176-383-8",
    abstract = "Retrieval-augmented generation has become the dominant paradigm for deploying large language models in knowledge-intensive applications, yet practitioners lack guidance on model selection when both quality and costs matter. We evaluate language models from 4B to 70B parameters, including PLLuM and Bielik families of Polish LLM, within a Polish Wikipedia-based RAG pipeline. Quality assessment uses GPT-4o pairwise comparison across 1,000 PolQA questions with bias mitigation and Bradley-Terry ranking, while energy measurements capture inference costs on NVIDIA H100 hardware. Our findings challenge conventional scaling assumptions: parameter scaling beyond 12B offers minimal quality gains, with mid-size PLLuM-12 matching 70B performance while reducing energy consumption by 83{\%}."
}