借助 LLM 增强的分层注意力网络迈向客观且无偏见的决策评估
Towards Objective and Unbiased Decision Assessments with LLM-Enhanced Hierarchical Attention Networks
AI总结:
本研究针对高风险决策中人类专家的认知偏见,提出增强型分层注意力网络 BGM-HAN 及 SAR 智能体工作流,经真实数据验证显著优于人类判断与替代模型。
摘要:
我们在做决策时有多客观和无偏见?本研究调查了人类专家在高风险决策过程中的认知偏见识别,质疑其在现实场景(如大学录取候选人评估)中的有效性。我们首先进行统计分析,评估当前流程中不同决策点之间的相关性,发现了暗示认知偏见和决策不一致的差异。这促使我们探索超越人类判断的偏见感知 AI 增强工作流。我们提出 BGM-HAN,一种结合 Byte-Pair Encoding、Gated Residual Connections 和 Multi-Head Attention 的增强型 Hierarchical Attention Network。以此作为骨干模型,我们进一步提出 Shortlist-Analyse-Recommend (SAR) 智能体工作流,以模拟现实世界的决策。实验表明,所提出的模型和智能体工作流均显著优于人类判断和替代模型,并已通过真实数据验证。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。