用大模型分析社交媒体文本中的价值冲突，推断个人道德判断。
SOLAR: Towards Characterizing Subjectivity of Individuals through Modeling Value Conflicts and Trade-offs
- 通过建模用户文本中的价值冲突与权衡，捕捉个体主观立场。
- 在争议性情境下推理准确率显著提升，整体表现更优。
- 可生成解释性结果，适合研究个体价值观与社会态度。
大型语言模型（LLMs）不仅在复杂推理任务中表现出色，也在需要主观决策的任务中展现强大能力。现有研究指出LLM生成内容在一定程度上具有主观基础，但对模型能否刻画个体层面主观性的探讨仍不充分。本文旨在通过分析社交媒体文本，表征个体主观性并推断其道德判断。提出SOLAR（Subjective Ground with Value Abstraction）框架，通过观察用户生成文本中的价值冲突与权衡，更精准地建模个体主观基础。实验结果表明，该框架在整体推理性能及争议情境下的表现均有提升。此外，定性分析显示SOLAR能提供关于个体价值偏好的解释，进一步支持其判断依据。
原文摘要 · Abstract (English)
Large Language Models (LLMs) not only have solved complex reasoning problems but also exhibit remarkable performance in tasks that require subjective decision making. Existing studies suggest that LLM generations can be subjectively grounded to some extent, yet exploring whether LLMs can account for individual-level subjectivity has not been sufficiently studied. In this paper, we characterize subjectivity of individuals on social media and infer their moral judgments using LLMs. We propose a framework, SOLAR (Subjective Ground with Value Abstraction), that observes value conflicts and trade-offs in the user-generated texts to better represent subjective ground of individuals. Empirical results show that our framework improves overall inference results as well as performance on controversial situations. Additionally, we qualitatively show that SOLAR provides explanations about individuals' value preferences, which can further account for their judgments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。