使用大型语言模型从双语食品标签中提取营养信息
Fatmah Y Assiri1, Mohammad D Alahmadi1, Mohammed A Almuashi2
1Software Engineering Department, College of Computer Science and Engineering, University of Jeddah, Jeddah 21493, Saudi Arabia.
Journal of imaging
|August 27, 2025
概括
大型语言模型 (LLM) 可以从食品标签中提取营养数据, 后处理显著提高了准确性,GPT-4o优于其他多语言食品标签分析模型.
科学领域:
- 食品科学
- 计算语言学
- 人工智能
背景情况:
- 食品产品标签对于消费者和监管机构如食品和药物管理局 (FDA) 来说至关重要.
- 多语言食品标签的手工转录是劳动密集且容易出错的.
- 自动从图像中提取营养信息对于在线杂货平台至关重要.
研究的目的:
- 研究大型语言模型 (LLM) 从多语言食品标签中提取营养数据的有效性.
- 为了比较不同LLM (GPT-4o,GPT-4V,Gemini) 在英语和阿拉伯语食品标签上的性能.
- 评估后处理技术对提取精度的改善的影响.
主要方法:
- 创建了一个294个食品标签的精心策划的数据集,
- 使用LLM从标签图像中提取营养信息.
- 使用经验分析和后处理技术来评估和提高提取精度.
主要成果:
- 与阿拉伯语相比,LLM在提取英语营养数据方面显示出更高的准确性.
- 后加工技术大大提高了营养元素和价值提取的整体准确性.
- 在此任务中,GPT-4o比GPT-4V和Gemini取得了更高的性能.
结论:
- 对于从食品标签中提取营养信息的自动化,
- 需要在LLM能力和后处理方面取得进一步的进步,以克服多语言数据的挑战,特别是阿拉伯语.
- 基于LLM的优化解决方案可以提高监管合规性和消费者信息的数据可访问性和准确性.
相关概念视频
Improving Translational Accuracy
11.8K
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...
11.8K
Protein Digestion
105.6K
Protein digestion begins in the stomach, where the highly acidic environment can easily disrupt protein structure by exposing the peptide bonds of polypeptide chains. After polypeptide chains are broken into individual amino acids by a series of digestive enzymes, the amino acids are transported to the liver via the bloodstream to produce energy.
105.6K
Health Literacy
4.1K
Health literacy is an individual's or a community's capacity to comprehend, receive, read, and use relevant healthcare information and services. The World Health Organization (WHO, 2018) defines health literacy as the cognitive and social skills that determine the ability of individuals to gain access to, understand, and use information in ways that promote and maintain good health. As a result, the WHO helps individuals manage long-term health concerns, participate in preventative...
4.1K
Translation
15.5K
Translation is the process of synthesizing proteins from the genetic information carried by messenger RNA (mRNA). Following transcription, it constitutes the final step in the expression of genes. This process is carried out by ribosomes, complexes of protein and specialized RNA molecules. Ribosomes, transfer RNA (tRNA), and other proteins produce a chain of amino acids—the polypeptide—as the end product of translation.
Translation Produces the Building Blocks of Life
Proteins are...
Translation Produces the Building Blocks of Life
Proteins are...
15.5K
Genetic Lingo
104.5K
Overview
104.5K
Protein Glycosylation
7.2K
Glycosylation, the most common post-translational modification for proteins, serves diverse functions. Adding sugars to proteins makes the proteins more resistant to proteolytic digestion. Glycosylated proteins can act as markers and receptors to promote cell-cell adhesion. Additionally, they have many essential quality control functions in the cell, such as correct protein folding and facilitating transport of misfolded proteins to the cytosol, which can be degraded.
Glycosylation occurs in...
Glycosylation occurs in...
7.2K


