BGM-HAN: A Hierarchical Attention Network for Accurate and Fair Decision Assessment on Semi-Structured Profiles

TL;DR

This paper introduces BGM-HAN, a hierarchical attention network that improves decision accuracy and fairness in semi-structured profile assessments, demonstrated through university admissions data.

Contribution

It presents a novel hierarchical attention model tailored for semi-structured data, enhancing interpretability and predictive accuracy over existing methods.

Findings

BGM-HAN outperforms state-of-the-art baselines in accuracy.

The model improves fairness in decision-making.

Experimental results validate the effectiveness of hierarchical representations.

Abstract

Human decision-making in high-stakes domains often relies on expertise and heuristics, but is vulnerable to hard-to-detect cognitive biases that threaten fairness and long-term outcomes. This work presents a novel approach to enhancing complex decision-making workflows through the integration of hierarchical learning alongside various enhancements. Focusing on university admissions as a representative high-stakes domain, we propose BGM-HAN, an enhanced Byte-Pair Encoded, Gated Multi-head Hierarchical Attention Network, designed to effectively model semi-structured applicant data. BGM-HAN captures multi-level representations that are crucial for nuanced assessment, improving both interpretability and predictive performance. Experimental results on real admissions data demonstrate that our proposed model significantly outperforms both state-of-the-art baselines from traditional machine learning to large language models, offering a promising framework for augmenting decision-making in domains where structure, context, and fairness matter. Source code is available at: https://github.com/junhua/bgm-han.