Metraipolis › archive › dc_f4635dc5b2a6

LLMs or Naive Bayes? Old Gems or New Ways — arXiv:2609.13185

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.13185
License (as archived): CC0-1.0
Archived: 2026-10-15T22:48:15.171Z
SHA-256 of the archived text: e2160f2b9f419dbd85240632d8b48d7001731534365fd73581b34161436d622f
Stable URL of this page: https://metraipolis.com/documento/dc_f4635dc5b2a6

How to cite

LLMs or Naive Bayes? Old Gems or New Ways — arXiv:2609.13185 — arXiv (en), https://arxiv.org/abs/2609.13185 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f4635dc5b2a6 (Metraipolis archive dc_f4635dc5b2a6, sha256 e2160f2b9f419dbd85240632d8b48d7001731534365fd73581b34161436d622f)

BibTeX

@misc{dcf4635dc5b2a6,
  title = {LLMs or Naive Bayes? Old Gems or New Ways — arXiv:2609.13185},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13185},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f4635dc5b2a6; sha256 e2160f2b9f419dbd85240632d8b48d7001731534365fd73581b34161436d622f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13185. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) prompt a recurring question in research computing: should classical methods like Naive Bayes (NB) be retired? We benchmark Complement Naive Bayes against zero-shot and few-shot LLMs spanning four model families and a 37x range in scale (27B to a 1T-parameter mixture-of-experts) across text classification tasks. LLMs dominate only in zero-data regimes (98.0% vs 88.2% on Amazon Polarity sentiment), and even that win is contamination-prone: on a low-contamination sentiment task NB beats the zero-shot LLM (81.7% vs 73.0%). However, once labeled data is available (e.g., AG News), NB reaches 89.1% accuracy, statistically indistinguishable from the zero-shot 27B LLM (89.0%) and better than the 397B frontier model (84.8%), at thousands of samples/sec on a commodity CPU. Fine-tuned DistilBERT reaches 90.6% but at far lower throughput than NB at batch size 1 (Table 2). Our measured GPU throughput analysis shows small-LLM batched inference is 40-486x slower than NB CPU inference (the multiplier depends strongly on the host CPU), exposing a structural gap bounded by memory bandwidth, with roughly two orders of magnitude lower energy per sample. For resource-constrained HPC practitioners performing text classification with labeled data, NB remains the optimal choice. We show the decision line is task-dependent (NB reaches LLM parity around $N \sim 10^4$ labels for topic classification, while zero-data sentiment favors the LLM at all N tested) and provide a Kubernetes Helm operator that automates model selection using configurable thresholds and verifiable Prometheus metrics.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2609.13185 — 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 2026-10-15T22:29:03.405Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).