---
title: "Evidence-grounded large language models guide perovskite solar cell design and optimization"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.00633v1"
permalink: "https://feed.astralor.com/items/itm_1471fa3bbe27427ca86ac83b"
published: "2026-10-31T04:57:32.000Z"
score: 57
channel: "tech"
tags: ["LLM","Evidence-grounded","Using","Here","PSM-Bench","OpenPerov","Structured-evidence"]
---

# Evidence-grounded large language models guide perovskite solar cell design and optimization

## 速览

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 establis…

## 关键点

- 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 ob…

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_1471fa3bbe27427ca86ac83b