Inter‐Rater Reliability of AI Scores: A Call to Move from Correlational to Factor Analytical Estimation

可靠性(半导体) 心理学 样品(材料) 估计 标准化 统计 等级间信度 样本量测定 蒙特卡罗方法 差异(会计) 应用心理学 计量经济学 人工智能 有效性 计算机科学 机器学习 分数 预测效度 增量有效性
作者
Andrew B. Speer
出处
期刊:Personnel Psychology [Wiley]
卷期号:79 (4): 483-504 被引量:1
标识
DOI:10.1111/peps.70036
摘要

ABSTRACT Artificial intelligence (AI), such as large language models (LLMs), is increasingly being used to score psychological and organizational constructs from text. However, the reliability and validity of these scores remains vital. Frequently, AI scores are treated as replicants of human ratings and inter‐rater reliability (IRR) is established by correlating AI and subject‐matter‐expert (SME) ratings. Yet, because LLMs may meaningfully differ from humans in ability to score text, correlating LLM scores with SME ratings is inappropriate because correlational approaches assume that AI and human scores are parallel, a condition that is unlikely and difficult to verify. This study proposes a factor‐analytic alternative in which AI scores and SME ratings are modeled as congeneric indicators of a common latent construct, estimating AI IRR as the squared standardized AI loading. Using a Monte Carlo simulation, correlational and CFA‐based IRR estimates were compared while manipulating true LLM and SME reliability, sample size, number of SME raters, and rater mean differences under ill‐structured rater designs. The simulations confirmed that when parallelism is violated, correlation‐based estimates (whether using single‐rater or composite SME ratings) are severely biased. In contrast, the proposed CFA framework accurately estimates AI IRR across diverse conditions, with precision improving as sample size, true IRR, and the number of SME raters increases. Furthermore, although ill‐structured designs reduce estimation accuracy, within‐rater standardization eliminated these inaccuracies. In conclusion, this paper urges researchers and practitioners to stop using correlational designs when estimating the IRR of LLM scores and offers best practice guidance going forward.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
96121abc完成签到,获得积分10
刚刚
刚刚
FashionBoy的应助被石榴采纳,获得10
1秒前
生动沛白完成签到 ,获得积分10
1秒前
Wwww发布了新的文献求助30
1秒前
loy完成签到,获得积分10
1秒前
MOMHANG完成签到,获得积分10
1秒前
下雨天睡个懒觉完成签到,获得积分10
1秒前
鬼医完成签到,获得积分10
2秒前
无花果的应助被雨滴油纸伞采纳,获得10
2秒前
CH完成签到,获得积分10
2秒前
2秒前
lx完成签到,获得积分10
2秒前
多买一只表完成签到 ,获得积分10
2秒前
烂漫的乐松完成签到,获得积分10
3秒前
七十三度发布了新的文献求助10
3秒前
外号胡一八完成签到 ,获得积分10
3秒前
白水完成签到,获得积分10
4秒前
傲慢帝完成签到,获得积分10
4秒前
杜小鱼发布了新的文献求助10
4秒前
kekeke完成签到 ,获得积分10
4秒前
华仔的应助被荷序采纳,获得10
4秒前
4秒前
666发布了新的文献求助10
4秒前
4秒前
4秒前
yin完成签到,获得积分20
5秒前
6秒前
无极微光的应助被xxz采纳,获得20
6秒前
缥缈听白完成签到,获得积分10
6秒前
6秒前
yexushifeng完成签到,获得积分10
6秒前
YSK819完成签到,获得积分10
7秒前
等待香薇发布了新的文献求助10
7秒前
kiminonawa发布了新的文献求助10
7秒前
7秒前
7秒前
Hello的应助被ph0307采纳,获得10
7秒前
july7292发布了新的文献求助10
8秒前
凌慕发布了新的文献求助10
8秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8180531
求助须知:如何正确求助?哪些是违规求助? 9570507
关于积分的说明 21812974
捐赠科研通 7776619
什么是DOI,文献DOI怎么找? 3433286
关于科研通互助平台的介绍 2557539
邀请新用户注册赠送积分活动 2479185