Saved in:
Bibliographic Details
Main Authors: Liu, Junhua, Lee, Roy Ka-Wei, Lim, Kwan Hui
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.17472
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913956413571072
author Liu, Junhua
Lee, Roy Ka-Wei
Lim, Kwan Hui
author_facet Liu, Junhua
Lee, Roy Ka-Wei
Lim, Kwan Hui
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_17472
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BGM-HAN: A Hierarchical Attention Network for Accurate and Fair Decision Assessment on Semi-Structured Profiles
Liu, Junhua
Lee, Roy Ka-Wei
Lim, Kwan Hui
Machine Learning
Artificial Intelligence
Information Retrieval
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.
title BGM-HAN: A Hierarchical Attention Network for Accurate and Fair Decision Assessment on Semi-Structured Profiles
topic Machine Learning
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2507.17472