Leakage-Aware LLM Augmentation for Attrition Prediction: A DecisionCentric Evaluation
Artificial Intelligence and Internet Studies · 2026
DOI: 10.65343/aiis.v2i2.141 ↗Kurz gefasst
Fachartikel in der Zeitschrift Artificial Intelligence and Internet Studies, 2026. Verfasst von Liao Weiquan und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Employee attrition is a high-cost, asymmetric decision problem plagued by data imbalance. To address this, we propose a leakage-aware, dual-network augmentation framework that integrates the semantic reasoning of Large Language Models (LLMs) with the distributional rigorousness of GAN discriminators. Specifically, we employ an autoregressive transformer (GReaT) as a generative "actor" to synthesize diverse minority samples, coupled with a post-hoc "critic" derived from a conditional GAN to strictly filter low-fidelity outliers. This actor-critic inspired loop ensures that synthetic records broaden coverage without introducing noise. We evaluate this pipeline using a rigorous protocol where all generation and filtering occur strictly within training folds to prevent leakage. Experiments on HR datasets show that moderate, critic-guided oversampling yields significant recall gains (e.g., raising recall from 45% to 53%) and improved F₁ scores compared to baselines, while maintaining calibration and discrimination (stable ROC-AUC). Furthermore, the approach preserves interpretability (SHAP) and fairness (low TPR gaps), offering HR practitioners a robust, decision-centric tool to identify at-risk employees without sacrificing transparency.
Zitieren
APA
Weiquan, L., Xu, J., & Panova, E. A. (2026). Leakage-Aware LLM Augmentation for Attrition Prediction: A DecisionCentric Evaluation. Artificial Intelligence and Internet Studies. https://doi.org/10.65343/aiis.v2i2.141
Vancouver
Weiquan L, Xu J, Panova EA. Leakage-Aware LLM Augmentation for Attrition Prediction: A DecisionCentric Evaluation. Artificial Intelligence and Internet Studies. 2026. doi:10.65343/aiis.v2i2.141
BibTeX
@article{Weiquan2026,
author = {Weiquan, Liao and Xu, Jiayangmei and Panova, Ekaterina A.},
title = {Leakage-Aware LLM Augmentation for Attrition Prediction: A DecisionCentric Evaluation},
journal = {Artificial Intelligence and Internet Studies},
year = {2026},
doi = {10.65343/aiis.v2i2.141}
}
EUVIMED