来自大型语言模型的标签噪声的影响产生了对诊断模型性能评估的注释
Mohammadreza Chavoshi1, Hari Trivedi1, Aawez Mansuri1
1Department of Radiology and Imaging Sciences, Emory University School of Medicine, 1364 Clifton Rd NE, Atlanta, GA 30322.
Radiology. Artificial intelligence
|December 24, 2025
概括
大型语言模型 (LLM) 可以在为人工智能 (AI) 模型评估标记数据时引入显著的偏差. 确保高LLM特异性至关重要,特别是在低流行情景中,以避免低估AI性能.
科学领域:
- 人工智能的人工智能
- 机器学习评估 机器学习评估
- 医疗信息学 医疗信息学
背景情况:
- 评估人工智能 (AI) 二元分类模型依赖于准确的数据标签.
- 大型语言模型 (LLM) 越来越多地用于数据注释,但它们可能引入标签噪音是令人担忧的.
研究的目的:
- 系统地调查LLM产生的标签噪声对人工智能二元分类模型实际性能评估的影响.
- 量化由疾病流行率调节的LLM标签错误如何影响AI模型性能估计的准确性.
主要方法:
- 使用合成数据集 (1万例) 开发了一个模拟框架,跨越不同流行情况 (10%至90%).
- LLM的灵敏度和特异性是独立变化的,并模拟了具有已知的性能的AI模型.
- 使用LLM生成的标签计算明显模型性能,使用分析和蒙特卡洛方法来确定性能边界和不确定性.
主要成果:
- 士学位标签质量显著影响了明显的AI模型性能,偏差严重依赖于疾病流行率.
- 在低患病率 (10%) 的环境中,LLM特异性降低导致AI模型灵敏度的大幅低估 (例如,90%的LLM特异性导致完美的模型明显灵敏度为53%).
- 在高患病率 (90%) 的环境中,LLM敏感度降低导致AI模型特异性的低估 (例如,90%的LLM敏感度为完美的模型带来了~53%的明显特异性).
结论:
- 由LLM生成的标签可以在AI模型评估中引入系统的,依赖于流行率的偏见.
- 高的LLM特异性对于准确的性能估计在低流行任务至关重要,以防止假阳性从不成比例的偏差敏感性.
- 仔细考虑LLM标签质量和流行率对于可靠的AI模型评估至关重要.
相关概念视频
Survival Tree
369
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
369
Detection of Gross Error: The Q Test
6.8K
When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...
6.8K
Documentation of Nursing Diagnosis
1.6K
The nurse documents nursing diagnoses and enters them into the patient record. The identified patient's nursing diagnosis is either written out with a plan of care or entered into the electronic health record.
In some settings, data-driven computerized decision support systems are in place, allowing for more accurate nursing diagnoses. The database within one of these systems includes diagnostic labels defining characteristics, activities, and indicators for nursing. A nurse enters...
In some settings, data-driven computerized decision support systems are in place, allowing for more accurate nursing diagnoses. The database within one of these systems includes diagnostic labels defining characteristics, activities, and indicators for nursing. A nurse enters...
1.6K
Labeling DNA Probes
9.2K
DNA probes are fragments of DNA labeled with a reporter tag to enable their detection or purification. The resulting labeled DNA probes can then hybridize to target nucleic acid sequences through complementary base-pairing, and may be used to recover or identify these regions.
Radioisotopes, fluorophores, or small molecule binding partners like biotin or digoxigenin, are the most widely used reporter tags for labeling DNA probes. These labels can be attached to the probe DNA molecule via...
Radioisotopes, fluorophores, or small molecule binding partners like biotin or digoxigenin, are the most widely used reporter tags for labeling DNA probes. These labels can be attached to the probe DNA molecule via...
9.2K
Formulating and Validating Nursing Diagnosis I
3.5K
A nursing diagnosis is written when the nurse recognizes a cluster of essential patient data indicating health problems treated with independent nursing interventions. The standardized terminologies of a nursing diagnosis help nurses identify and treat patients' problems. Every electronic health record that uses nursing diagnosis must employ standard diagnostic terminology. Developing an efficient, individualized care plan begins with accurate nursing diagnoses.
There are thirteen domains...
There are thirteen domains...
3.5K
Sensitivity, Specificity, and Predicted Value
1.2K
In healthcare diagnostics, laboratory tests play a crucial role in identifying and diagnosing a wide range of medical conditions. However, interpreting test results is not always straightforward. An abnormal test result does not always confirm the presence of a disease, just as a normal result does not guarantee its absence. To assess the reliability of these diagnostic tools, healthcare practitioners rely on two key statistical indicators: sensitivity and specificity.
Sensitivity is the...
Sensitivity is the...
1.2K

