Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models

2026-08-19

AI Summary

研究通过自提示和跨模型共识方法，利用大型语言模型从科学文献中提取复杂信息，提出四种工作流程以提高数据提取的准确性与效率。

Abstract

Accurately extracting nuanced, contextualized data from research articles is laborious and time intensive. Here, we investigate the performance of frontier, browser-based large language models (LLMs) to extract highly contextualized information. We demonstrate four escalating workflows, 1) given an expert curated prompt and research articles, most frontier LLMs perform well at data extraction, however can struggle with interpreting scientific context and nuance, 2) given simple instructions, LLMs can author their own prompts which were almost as eNective as expert-written prompts, 3) autonomous discovery of research literature was diNicult, agents either missed or hallucinated references, and 4) LLMs can create new datasets from published guidelines that closely match human-expert judges, but still require a human-in-the-loop. Together, these findings define an auditable division of labour in which experts specify the evidence standard, models cross-check repeated extractions and researchers resolve disputed cases, providing a practical route to scaling scientific data curation without relinquishing expert oversight.

Problem

• data extraction
• scientific literature
• large language models
• contextualized information

Innovation

• self-prompting
• cross-model consensus
• large language models (LLMs)
• data extraction