Metraipolis › archive › dc_cc226ccbc184

Concept-Guided Prompting Strategies Increase Diversity in LLM-Generated Recipe Populations — arXiv:2611.01171

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01171
License (as archived)
CC0-1.0
Archived
2026-11-03T10:22:11.045Z
SHA-256 of the archived text
6f67eb96750f72d8b3dec7580dcd85510ab681058ba3775a3748fc63d4cd02c5
Stable URL of this page
https://metraipolis.com/documento/dc_cc226ccbc184

How to cite

Concept-Guided Prompting Strategies Increase Diversity in LLM-Generated Recipe Populations — arXiv:2611.01171 — arXiv (en), https://arxiv.org/abs/2611.01171 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc226ccbc184 (Metraipolis archive dc_cc226ccbc184, sha256 6f67eb96750f72d8b3dec7580dcd85510ab681058ba3775a3748fc63d4cd02c5)
BibTeX
@misc{dccc226ccbc184,
  title = {Concept-Guided Prompting Strategies Increase Diversity in LLM-Generated Recipe Populations — arXiv:2611.01171},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01171},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc226ccbc184; sha256 6f67eb96750f72d8b3dec7580dcd85510ab681058ba3775a3748fc63d4cd02c5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01171. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Novelty in solution generation supports automated discovery, but LLM outputs can remain repetitive. To address this, we propose a simple concept-guided prompting method that generates thematic concepts before responses within each of these concepts. To demonstrate, we generated 1,000 recipes for a recipe book task and compared the results against a human-authored corpus. Two naive prompting strategies were compared as baselines. Concept-guided prompting outperformed both baselines in all cases and reached semantic coverage of 47.0% versus 35.1% and 13.1% in respective prior-title and nonce prompt strategies. These findings suggest broader population exploration and diversity, but remain contained to this specific task. Further work is needed to determine the quality of solutions and generalizability.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.01171 — 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 2026-11-03T10:19:49.811Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).