Metraipolis › archive › dc_1fff86cef321

Evidence-grounded large language models guide perovskite solar cell design and optimization — arXiv:2611.00633

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00633
License (as archived)
CC0-1.0
Archived
2026-11-03T11:01:25.672Z
SHA-256 of the archived text
e009e02143a8563d82e6d7aa3f6c7097d6484ebc4a32ca5e1bbf1b9bc91da4d4
Stable URL of this page
https://metraipolis.com/documento/dc_1fff86cef321

How to cite

Evidence-grounded large language models guide perovskite solar cell design and optimization — arXiv:2611.00633 — arXiv (en), https://arxiv.org/abs/2611.00633 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1fff86cef321 (Metraipolis archive dc_1fff86cef321, sha256 e009e02143a8563d82e6d7aa3f6c7097d6484ebc4a32ca5e1bbf1b9bc91da4d4)
BibTeX
@misc{dc1fff86cef321,
  title = {Evidence-grounded large language models guide perovskite solar cell design and optimization — arXiv:2611.00633},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00633},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1fff86cef321; sha256 e009e02143a8563d82e6d7aa3f6c7097d6484ebc4a32ca5e1bbf1b9bc91da4d4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00633. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Using large language models to interpret experimental evidence, design discriminating experiments and formulate well-supported mechanistic explanations remains a central challenge in materials research. Here we establish PSM-Bench, an 800-question benchmark developed by perovskite researchers to evaluate scientific reasoning in perovskite photovoltaics. We also introduce OpenPerov, an expert-informed language-model framework that learns from expert-calibrated evidence records reconstructed from 4,532 articles; these records link experimental strategies, controls and observations to mechanistic interpretations. Structured-evidence adaptation outperformed conventional question-answer training, and OpenPerov Flash ranked first among 13 closed-book systems. OpenPerov Pro raised Scientific Mastery further, from 87.6 to 89.1, by revising selected passages with retrieved evidence. On questions derived from subsequent studies, both models also outscored expert-authored answers. In an experimental test of self-assembled monolayer design, OpenPerov selected a K analogue that outperformed the Na analogue preferred by experts. Devices incorporating the selected contact reached a power conversion efficiency of 27.05% and retained 96.74% of their steady-state reference efficiency after 1,000 h of dark thermal ageing at 85 $^\circ$C. These results show that reconstructed scientific reasoning provides an effective basis for building domain models that interpret experiments and inform materials design.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.00633 — 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 2026-11-03T10:59:45.733Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).