[论文解读] Surveying Attitudinal Alignment Between Large Language Models Vs. Humans Towards 17 Sustainable Development Goals

Qing Yang Steve Wu, Ying Xu+9 more|arXiv (Cornell University)|Apr 22, 2024

Sustainability and Climate Change Governance被引用 7

一句话总结

该论文调查大型语言模型（LLMs）与人类在17个可持续发展目标（SDGs）上的态度一致性，分析差异、风险，以及使AI符合可持续发展目标的对齐策略。

ABSTRACT

Large Language Models (LLMs) have emerged as potent tools for advancing the United Nations' Sustainable Development Goals (SDGs). However, the attitudinal disparities between LLMs and humans towards these goals can pose significant challenges. This study conducts a comprehensive review and analysis of the existing literature on the attitudes of LLMs towards the 17 SDGs, emphasizing the comparison between their attitudes and support for each goal and those of humans. We examine the potential disparities, primarily focusing on aspects such as understanding and emotions, cultural and regional differences, task objective variations, and factors considered in the decision-making process. These disparities arise from the underrepresentation and imbalance in LLM training data, historical biases, quality issues, lack of contextual understanding, and skewed ethical values reflected. The study also investigates the risks and harms that may arise from neglecting the attitudes of LLMs towards the SDGs, including the exacerbation of social inequalities, racial discrimination, environmental destruction, and resource wastage. To address these challenges, we propose strategies and recommendations to guide and regulate the application of LLMs, ensuring their alignment with the principles and goals of the SDGs, and therefore creating a more just, inclusive, and sustainable future.

研究动机与目标

• 评估LLM对每个SDG的态度与人类态度及支持程度之比较。
• 识别LLMs与人类在理解、类似情感反应与决策过程中的差异来源。
• 检视导致态度差距的文化、区域及数据相关因素。
• 评估错位可能带来的危害并提出SDG相关AI治理与监管策略。

提出的方法

• 对LLM对17个SDGs的态度以及与人类态度的比较进行全面文献综述。
• 分析驱动态度差异的因素，包括训练数据偏见、情境理解以及伦理价值观。
• 讨论诸如不平等、歧视、环境影响和资源浪费等风险。
• 提出引导和规范SDG对齐LLM部署的策略与建议。

实验结果

研究问题

• RQ1 在对17个SDG的态度与支持上，LLMs与人类之间存在哪些差异？
• RQ2 关于SDGs，LLMs与人类之间态度差异的主要原因（数据、情境、伦理）是什么？
• RQ3 忽视LLM态度对齐与SDGs相关的风险有哪些，如何减轻？
• RQ4 哪些策略可以确保LLMs在实践中与SDG原则保持一致？
• RQ5 治理框架应如何规范应用LLMs以支持可持续发展？

主要发现

• LLMs与人类在对SDG相关议题的理解、情感与情境解读方面存在显著差异。
• 数据偏见、历史偏见以及有限的情境理解可能使LLM输出偏离以人为本的SDG优先级。
• 忽视LLM态度对齐可能加剧社会不平等、歧视和环境伤害。
• 对齐策略和监管建议有助于引导LLM部署走向公平和可持续的结果。
• LLMs有助于通过数据分析和信息传播促进SDG进展，但需要谨慎治理以避免伤害。