相关实验视频
Updated: Feb 5, 2026

13:10
Title Cell Encapsulation by Droplets
Published on: October 1, 2007
9.0K
系统性审查中标题和摘要选的紧的大型语言模型:可行性,准确性和工作量减少的评估
Antonio Sciurti1, Giuseppe Migliara2, Leonardo Maria Siena1
1Department of Public Health and Infectious Diseases, University of Rome La Sapienza, Italy.
Research synthesis methods
|February 4, 2026
概括
紧的大型语言模型 (LLM) 对系统审查选具有很高的灵敏度,大大降低了工作量. 虽然不精确,但它们为标题和摘要审查提供了可行的,具有成本效益的解决方案.
科学领域:
- 医疗信息学 医疗信息学
- 基于证据的研究.
- 医疗保健中的人工智能
背景情况:
- 系统性审查对于基于证据的研究至关重要,但涉及耗时的标题和摘要选.
- 自动化这个选过程可以平衡效率和准确性.
研究的目的:
- 评估三种紧的大型语言模型 (LLM) 在选系统审查标题和摘要中的可行性,准确性和工作量减少潜力.
- 为了比较GPT-4o mini,Llama 3.1 8B和Gemma 2 9B用于此任务.
主要方法:
- 三个紧的LLM (GPT-4o mini,Llama 3.1 8B,Gemma 2 9B) 被用来选来自三个现有的系统性审查的标题和摘要.
- 通过使用结构化提示符,LLM在0-100纳入量级上对记录进行了评分.
- 性能指标包括平衡的准确性,灵敏度,特异性和预测值,在25级,50级和75级的评级值下计算.
主要成果:
- 在包含的记录中,LLM表现出高灵敏度 (高达100%),但精度低 (<10%).
- 通过更高的评级值 (50%和75%的最佳值) 提高了具体性和工作量节省.
- GPT-4o迷你是最快的 (大约. 40分钟) 的API成本 ($0.14-$1.93/review);Llama 3.1 8B和Gemma 2 9B的速度更慢 (大约为0.14-$1.93/review);Llama 3.1 8B和Gemma 2 9B的速度更慢 (大约为0.14-$1.93/review);Llama 3.1 8B和Gemma 2 9B的速度更慢 (大约为0.14-$1.93/review);Llama 3.1 8B和Gemma 2 9B的速度更慢 (大约为0.14-$1.93/review);Llama 3.1 8B和Gemma 2 9B的速度更慢. 4小时),但在本地运行时是免费的.
结论:
- 紧的LLM是系统审查标题/摘要选的高度敏感的工具,可显著减少工作负载.
- 高特异性值在更高的值下实现,平衡成本和处理时间.
- 尽管不精确,但高灵敏度和工作量减少使LLM在系统审查选中具有价值.
相关概念视频
Uncertainty in Measurement: Accuracy and Precision
101.8K
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value.
101.8K
Compact Bone
16.6K
Most bones contain compact and spongy osseous tissue, but their distribution and concentration vary based on the bone's overall function.
Compact bone, also called cortical bone, is the denser, stronger of the two types of bone tissue. It is found under the periosteum and in the diaphyses of long bones, where it provides support and protection. The microscopic structural unit of compact bone is called an osteon, or haversian system. Each osteon is composed of concentric rings of calcified...
Compact bone, also called cortical bone, is the denser, stronger of the two types of bone tissue. It is found under the periosteum and in the diaphyses of long bones, where it provides support and protection. The microscopic structural unit of compact bone is called an osteon, or haversian system. Each osteon is composed of concentric rings of calcified...
16.6K
Language
917
Language is a unique communication system that uses words and systematic rules to organize and transmit information. Unlike other forms of communication, which may involve postures, movements, odors, or vocalizations, language relies on symbols and grammar. This makes human communication distinct from that of other species, who also communicate but do not use language in the same way humans do.
Corballis and Suddendorf (2007) and Tomasello and Rakoczy (2003) highlight the role of language in...
Corballis and Suddendorf (2007) and Tomasello and Rakoczy (2003) highlight the role of language in...
917
Radical Formation: Abstraction
4.4K
The electron of an atom can be abstracted from a compound by a relatively unstable radical to generate a new radical of relatively greater stability. For example, an initiator which forms radicals by homolysis can abstract a suitable species like a hydrogen atom or a halogen atom from a compound to generate a new radical. This ability of radicals to propagate by abstraction is a crucial feature of radical chain reactions.
Even though homolysis produces radicals, it is different from radical...
Even though homolysis produces radicals, it is different from radical...
4.4K
Compacting Factor test
587
The compacting factor test is a method used to assess the workability of concrete. It is especially suitable for concrete mixes containing aggregates up to one and a half inches in size. This test involves specialized equipment consisting of two truncated cone-shaped hoppers and a cylinder, all with polished interior surfaces to minimize friction.
The procedure begins by placing concrete into the upper hopper without any compaction. Once filled, the bottom door of this hopper is opened,...
The procedure begins by placing concrete into the upper hopper without any compaction. Once filled, the bottom door of this hopper is opened,...
587
Improving Translational Accuracy
14.9K
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...
14.9K

