发表机构
Georgia State University; University of Pittsburgh（佐治亚州立大学; 匹兹堡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对LLM错误常逃过人工审核的问题，提出信息可检索性是有效监督的前提，通过两项640人实验发现自我解释和提示支持的重新激活可提升错误检测，为人类监督LLM提供了实用方案。
AI 中文摘要
大型语言模型（LLM）正越来越多地融入组织工作中，但它们的错误常逃过人工审核。此前研究将这类失败归因于用户审核LLM输出的能力或参与度。我们提出一种基于检索的人类监督解释，认为当审核相关信息在审核时对用户可访问，错误检测会更有效。在两项针对640名面向客户员工的随机实地实验中，我们发现，自我生成的解释能提升错误检测效果并增强对验证相关推理的回忆，而重新激活此类推理的提示有助于在反复使用LLM时维持检测效果。理论上，我们确定信息可检索性是有效监督的独特前提，并明确生成编码和提示支持的重新激活是构建与维持该前提的机制。实践中，随着LLM使用成为常规，轻量级的入职自我解释和日常检索提示可让人类监督更具韧性。
英文摘要
Large language models (LLMs) are increasingly embedded in organizational work, yet their errors often pass human review. Prior research locates such failures in users' capability to review LLM output or their engagement in doing so. We develop an alternative, retrieval-based account of human oversight and posit that error detection is more effective when oversight-relevant information is accessible to users at the moment of review. Across two randomized lab-in-the-field experiments with 640 customer-facing employees, we show that self-generated explanations improve error detection and strengthen recall of verification-relevant reasoning, while cues that reactivate such reasoning help sustain detection under repeated LLM use. Theoretically, we identify information retrievability as a distinct precondition for effective oversight and specify generative encoding and cue-supported reactivation as mechanisms that build and sustain it. Practically, lightweight onboarding self-explanations and daily retrieval cues can make human oversight more resilient as LLM use becomes routine.
