暴力死亡叙述的监督自然语言处理分类:一个紧的大型语言模型的开发和评估
1Feinberg School of Medicine, Northwestern University, 750 N Lakeshore, Chicago, IL, 60611, United States, 1 2487613116.
JMIR AI
|July 3, 2025
概括
这项研究表明,紧的大型语言模型 (LLM) 可以使用非结构化数据预测暴力死亡情况. 充分的培训数据是关键,精细的语言提高了准确性,尽管在人口统计学方面仍然存在一些偏见.
科学领域:
- 计算流行病学计算流行病学
- 公共卫生信息学 公共卫生信息学
- 自然语言处理 (NLP) 是一种自然语言处理.
背景情况:
- 国家暴力死亡报告系统 (NVDRS) 现在包括全面的执法和验尸报告,为NLP暴力研究提供了巨大的潜力.
- 这些报告中的非结构化叙事数据为先进的分析技术提供了独特的机会.
研究的目的:
- 评估监督NLP的应用,特别是使用紧的大型语言模型 (LLM),以预测暴力死亡的情况和类型.
- 评估数据预处理,数量和构成对NLP模型在NVDRS中的性能的影响.
主要方法:
- 应用于distilBERT,一个紧的LLM,从NVDRS的非结构化的叙事数据.
- 模拟了预处理和训练数据特征对模型性能的影响,测量F1分数,精度,回忆和虚假负面率.
- 通过比较F1分数,评估了跨种族,种族和性别子组的模型偏见.
主要成果:
- 一个紧的LLM需要至少1500个案例才能达到F1得分为0.6和假负率为0.01-0.05.
- 取代特定领域的术语显著改善了模型性能.
- 为了解决阶级不平衡,过量抽样并没有显著提高F1分数.
- 观察到种族/族群 (0.2-0.25) 和性别 (0.12-0.2) 之间的F1分数差异.
结论:
- 紧的LLM在不平衡的NVDRS数据上的监督NLP任务中是可行的,只要提供足够的训练数据.
- 模拟突出了基于LLM的NLP应用程序的预处理和训练数据策略的重要性.
- 虽然有效,但这些模型显示了人口群体之间的绩效差异,表明需要进一步的偏见减轻研究.
相关概念视频
Language and Cognition
456
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.
456
Language Development
460
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...
460
Language
430
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...
430
Stereotype Content Model
14.9K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.9K
Components of Language
410
Language, whether spoken, signed, or written, consists of specific components: lexicon and grammar. The lexicon is the vocabulary of a language, comprising its words. Grammar is the set of rules used to convey meaning through the lexicon. For example, English grammar adds “-ed” to most verbs to indicate past tense. Words are formed by combining phonemes, which are the basic sound units of a language. Different languages have different sets of phonemes (e.g., “ah” vs.
410
Lethal Alleles
15.7K
Agouti: A Lethal Allele
Lucien Cuénot discovered lethal alleles in 1905 while studying the inheritance of coat color in mice. The agouti gene is responsible for the color of the coat in mice. This gene codes for an agouti-signaling protein, which is responsible for melanin distribution in mammals. The wild-type allele gives rise to gray-brown coat color in mice, while the mutant allele gives rise to yellow coat color. In addition to coat color, the agouti gene is associated with the yellow...
Lucien Cuénot discovered lethal alleles in 1905 while studying the inheritance of coat color in mice. The agouti gene is responsible for the color of the coat in mice. This gene codes for an agouti-signaling protein, which is responsible for melanin distribution in mammals. The wild-type allele gives rise to gray-brown coat color in mice, while the mutant allele gives rise to yellow coat color. In addition to coat color, the agouti gene is associated with the yellow...
15.7K


