Metraipolis › archive › dc_07daca28cc6c

Tug of Watts: A study on the Energy - Accuracy Trade-off of Large Language Models on Medical Question Answering Tasks — arXiv:2611.02889

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02889
License (as archived)
CC0-1.0
Archived
2026-11-03T10:58:44.209Z
SHA-256 of the archived text
e2cc0ed6b59bc25002565f0b45c1816bd6ead5608be98bc9a3fa0085e560afe2
Stable URL of this page
https://metraipolis.com/documento/dc_07daca28cc6c

How to cite

Tug of Watts: A study on the Energy - Accuracy Trade-off of Large Language Models on Medical Question Answering Tasks — arXiv:2611.02889 — arXiv (en), https://arxiv.org/abs/2611.02889 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_07daca28cc6c (Metraipolis archive dc_07daca28cc6c, sha256 e2cc0ed6b59bc25002565f0b45c1816bd6ead5608be98bc9a3fa0085e560afe2)
BibTeX
@misc{dc07daca28cc6c,
  title = {Tug of Watts: A study on the Energy - Accuracy Trade-off of Large Language Models on Medical Question Answering Tasks — arXiv:2611.02889},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02889},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_07daca28cc6c; sha256 e2cc0ed6b59bc25002565f0b45c1816bd6ead5608be98bc9a3fa0085e560afe2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02889. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) are increasingly used in medical question answering (QA) systems. While recent works aim at incrementally improving the downstream task accuracy, an empirical estimation of the models' energy consumption and the associated carbon footprints is often overlooked. In this study, we demonstrate how practitioners can estimate energy consumption and arrive at reliable emission estimates for medical QA tasks available in the OpenMedical-LLM leaderboard by investigating 13 LLMs from 3 model families ranging from 270M to 14B parameters. We discuss how one can critically interpret energy versus accuracy trade-offs for a set of models for a given task. With this work, we underline that reporting disjoint energy and accuracy metrics alone does not suffice for careful trade-off assessments, but it also demands systematic construction and interpretation of joint trade-off metrics. We envisage such studies aiding practitioners in adopting better and more efficient models for their task and helping them become active participants in building sustainable LLM pipelines.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.02889 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T10:49:38.692Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).