BGM-HAN: A Hierarchical Attention Network for Accurate and Fair Decision Assessment on Semi-Structured Profiles
This work addresses fairness and accuracy in decision-making for high-stakes domains like admissions, presenting an incremental enhancement to existing hierarchical learning methods.
The paper tackles the problem of cognitive biases in high-stakes decision-making, such as university admissions, by proposing BGM-HAN, a hierarchical attention network that models semi-structured applicant data, achieving significant performance improvements over state-of-the-art baselines.
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.