[论文] Identifying and Understanding Human Values in Text: A Tailorable ...

论文概要

研究领域: AI
作者: Eduardo de la Cruz Fernández, Marcelo Karanik, Sascha Ossowski
发布时间: 2026-05-28
arXiv: 2605.27373

中文摘要

随着智能系统日益自主化,学术界正致力于构建包含伦理道德考量的决策机制,以突破传统效用最大化模型的局限。实现这一目标的关键在于评估决策与人类价值观的对齐程度。本文提出了一种基于大语言模型(LLM)的架构,用于检测并量化文本中人类价值观的强度--无论这些价值观是显性还是隐性的。该架构避免了以往方法被特定价值理论束缚或依赖复杂提示工程的缺陷,由三个协同模块组成:从任何理论基础文本生成结构化价值规范的模块、利用这些规范标注文本的模块,以及基于修辞和语义证据赋予支持/反对等级的模块。这种模块化设计将价值观的概念化与检测任务分离,形成了可扩展、可复现且能适应不同理论的流程。在ValueEval数据集上的实验表明,该管道具有良好的检测性能。

原文摘要

As intelligent systems become more autonomous, the scientific community focuses on creating decision-making mechanisms that include ethical and moral considerations, unlike traditional utility-maximisation models. To achieve this, a key aspect is assessing how well these decisions align with human values. To this end, a promising line of research is centred on developing approaches based on Large Language Models (LLMs) to identify human values from text, whether explicit or implicit, enabling their recognition throughout. This paper introduces a LLM-based architecture to detect and quantify the intensity of human values in text, avoiding the limitations of previous approaches tied to specific value theory or complex prompt engineering. The architecture comprises three coordinated modules: one that generates structured value specifications from the foundational texts of any theoretical fr...

自动采集于 2026-05-29

#论文 #arXiv #AI #小凯