Metraipolis › archive › dc_84b2bc53dc7a

The Value of Not Knowing: How Fresh Eyes through Naive LLMs Fuel Creativity — arXiv:2611.11725

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.11725
License (as archived)
CC0-1.0
Archived
2026-11-10T18:41:30.294Z
SHA-256 of the archived text
c1541f95b9c6f600e6c61bdd9d4cca94b2ec32d9c7a7b0f1ebf6dbe4c3c150f0
Stable URL of this page
https://metraipolis.com/documento/dc_84b2bc53dc7a

How to cite

The Value of Not Knowing: How Fresh Eyes through Naive LLMs Fuel Creativity — arXiv:2611.11725 — arXiv (en), https://arxiv.org/abs/2611.11725 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_84b2bc53dc7a (Metraipolis archive dc_84b2bc53dc7a, sha256 c1541f95b9c6f600e6c61bdd9d4cca94b2ec32d9c7a7b0f1ebf6dbe4c3c150f0)
BibTeX
@misc{dc84b2bc53dc7a,
  title = {The Value of Not Knowing: How Fresh Eyes through Naive LLMs Fuel Creativity — arXiv:2611.11725},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.11725},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_84b2bc53dc7a; sha256 c1541f95b9c6f600e6c61bdd9d4cca94b2ec32d9c7a7b0f1ebf6dbe4c3c150f0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11725. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Many major scientific advances come from approaching a problem with a new or novel perspective. While large language models (LLMs) with internet-scale knowledge seem poised to take such perspectives, their consistent generation remains elusive. Instead, models are drawn to dominant views and preexisting, in-field bias. To explore the potential of fresh eyes to increase creativity, this paper proposes naive LLMs, models that are made intentionally ignorant of a specific topic. Through deprivation in training or intentional forgetting, naive models are unburdened by existing dogma, allowing them to be free to make new associations and conjectures. These naive models can then be paired with a stronger mentor model that can refine their unique perspectives into concrete proposals. For the 1B and 7B models tested in this paper, naive models consistently produce seed ideas that are more novel and useful than baseline counterparts, and mentor refinement improves the ideas even further. Thus, contrary to the prevailing tradition of scaling up training data, we demonstrate a case where less information is actually more powerful, in particular when the aim is to discover genuinely outside-the-box solutions.

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); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.11725 — 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 2026-11-10T18:37:37.519Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).