Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Junhua, Lim, Kwan Hui, Lee, Roy Ka-Wei
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2411.08504
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915019115986944
author Liu, Junhua
Lim, Kwan Hui
Lee, Roy Ka-Wei
author_facet Liu, Junhua
Lim, Kwan Hui
Lee, Roy Ka-Wei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_08504
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Objective and Unbiased Decision Assessments with LLM-Enhanced Hierarchical Attention Networks
Liu, Junhua
Lim, Kwan Hui
Lee, Roy Ka-Wei
Computation and Language
Artificial Intelligence
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.
title Towards Objective and Unbiased Decision Assessments with LLM-Enhanced Hierarchical Attention Networks
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2411.08504