# Towards Objective and Unbiased Decision Assessments with LLM-Enhanced Hierarchical Attention Networks

arXiv: https://arxiv.org/abs/2411.08504 · HTML: https://mlsanity.com/paper/2411.08504/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 29 references that are in the map.
- First posted on arXiv 13 Nov 2024.

## Builds on (most cited first, 10 of 10)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [Cognitive Bias in Decision-Making with LLMs](https://mlsanity.com/paper/2403.00811/) (2024)
- [D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling Algorithmic Bias](https://mlsanity.com/paper/2208.05126/) (2022)
- [Fair Machine Guidance to Enhance Fair Decision Making in Biased People](https://mlsanity.com/paper/2404.05228/) (2024)
- [Learning Identity Mappings with Residual Gates](https://mlsanity.com/paper/1611.01260/) (2016)
- [Overcoming Anchoring Bias: The Potential of AI and XAI-based Decision Support](https://mlsanity.com/paper/2405.04972/) (2024)
- [Pruning and Sparsemax Methods for Hierarchical Attention Networks](https://mlsanity.com/paper/2004.04343/) (2020)

## Abstract (arXiv)

How objective and unbiased are we while making decisions? This work investigates cognitive bias identification in high-stake decision making process by human experts, questioning its effectiveness in real-world settings, such as candidates assessments for university admission. We begin with a statistical analysis assessing correlations among different decision points among in the current process, which discovers discrepancies that imply cognitive bias and inconsistency in decisions. This motivates our exploration of bias-aware AI-augmented workflow that surpass human judgment. We propose BGM-HAN, an enhanced Hierarchical Attention Network with Byte-Pair Encoding, Gated Residual Connections and Multi-Head Attention. Using it as a backbone model, we further propose a Shortlist-Analyse-Recommend (SAR) agentic workflow, which simulate real-world decision-making. In our experiments, both the proposed model and the agentic workflow significantly improves on both human judgment and alternative models, validated with real-world data.