人工智能驱动的摘要生成:在PRISMA-A框架下通过定制提示来评估LLM
Gizem Boztaş Demi̇r1, Şule Gökmen2, Yağızalp Süküt2
1Department of Orthodontics, Gulhane Faculty of Dental Medicine, University of Health Sciences, Ankara, Turkey. gizem.demir@sbu.edu.tr.
BMC oral health
|October 11, 2025
概括
聊天GPT-4o和Gemini Pro可以生成结构化摘要用于系统性审查. 聊天GPT-4o获得了更高的质量评分,特别是在报告所包含的研究和合成结果方面,证明了它在遵守PRISMA摘要检查清单方面的卓越表现.
科学领域:
- 科学出版中的人工智能
- 用于医学文献的自然语言处理.
背景情况:
- 系统性审查和元分析对于基于证据的牙科至关重要.
- 根据像PRISMA摘要清单这样的标准报告这些审查可能会耗时.
- 大型语言模型 (LLM) 为高效的抽象生成提供了潜在的解决方案.
研究的目的:
- 为了比较ChatGPT-4o和Gemini Pro在从全文系统审查中生成结构化摘要的性能.
- 根据遵守PRISMA摘要 (PRISMA-A) 检查清单来评估抽象生成.
- 评估一个定制提示的实用性,以LLM为基础的抽象创作在牙矯正.
主要方法:
- 分析了来自Q1排名的正统牙科期刊 (自2019年以来) 的162个系统评论和元分析.
- 全文文章由ChatGPT-4o和Gemini Pro使用与PRISMA-A检查清单一致的提示符进行处理.
- 抽象质量通过从PRISMA-A检查清单获得的量身定制的整体质量评分 (OQS) 来得分;可靠性和模型比较被统计评估.
主要成果:
- 这两种LLM都产生了令人满意的PRISMA-A合规摘要.
- 聊天GPT-4o的整体质量评分 (OQS) 始终高于双子Pro (平均OQS为21.67比21.00,p<0.001).
- 聊天GPT-4o在"包括研究"和"结果综合"部分表现出色,产生了更完整和更连贯的输出.
结论:
- 聊天GPT-4o和双子Pro都可以生成符合PRISMA-A的摘要.
- 与Gemini Pro.相比,ChatGPT-4o表现出优越的质量和遵守PRISMA-A检查清单.
- 开发的Prompt和LLM方法显示了在以证据为基础的牙科和医学研究中更广泛的应用的前景,以简化报告.
相关概念视频
Language Development
848
Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
848
Statically Indeterminate Problem Solving
690
Statically indeterminate problems are those where statics alone can not determine the internal forces or reactions. Consider a structure comprising two cylindrical rods made of steel and brass. These rods are joined at point B and restrained by rigid supports at points A and C. Now, the reactions at points A and C and the deflection at point B are to be determined. This rod structure is classified as statically indeterminate as the structure has more supports than are necessary for maintaining...
690
Language and Cognition
711
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
711
Improving Translational Accuracy
14.1K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
14.1K
Improving Translational Accuracy
3.5K
3.5K
Automatic Processing and Automatic Social Behavior
214
Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...
214

