Metraipolis › archive › dc_3d8a4e1fa5d5

Cascaded Batch Prompting — arXiv:2608.27038

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.27038
License (as archived): CC0-1.0
Archived: 2026-10-17T15:20:14.910Z
SHA-256 of the archived text: be190713f07d457e9946c49b49edad5e78e69b2aa26e7eb2b3f4d84cd8c8bc47
Stable URL of this page: https://metraipolis.com/documento/dc_3d8a4e1fa5d5

How to cite

Cascaded Batch Prompting — arXiv:2608.27038 — arXiv (en), https://arxiv.org/abs/2608.27038 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3d8a4e1fa5d5 (Metraipolis archive dc_3d8a4e1fa5d5, sha256 be190713f07d457e9946c49b49edad5e78e69b2aa26e7eb2b3f4d84cd8c8bc47)

BibTeX

@misc{dc3d8a4e1fa5d5,
  title = {Cascaded Batch Prompting — arXiv:2608.27038},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27038},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3d8a4e1fa5d5; sha256 be190713f07d457e9946c49b49edad5e78e69b2aa26e7eb2b3f4d84cd8c8bc47},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27038. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Although batch prompting makes large language model inference more efficient by processing multiple instances simultaneously, it suffers from unpredictable downstream task performance. We propose cascaded batch prompting, a two-stage approach designed to resolve the unpredictability of conventional batch prompting by disentangling complex reasoning from symbol grounding. Experiments on multiple-choice question answering and natural language inference demonstrate that the proposed method outperforms the standard single prompting baseline while achieving a speedup proportional to batch size, establishing a new state of the art on the Pareto frontier.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.27038 — 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 2026-10-17T15:15:18.084Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).