LLMs measure human values in social media with new annotation method

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-09 15:55

研究人员开发了一种使用LLM来衡量社交媒体文本中表达的人类价值观的方法。该研究利用了非英语帖子和Schwartz的基本人类价值观理论，发现不同的LLM对价值观的解读不同。通过迭代式提示校准和错误分析，提高了LLM标注的准确性，然后将这些标注转移到编码器模型上进行可扩展预测。 AI

影响这项研究提供了一种分析社交媒体主观内容的新方法，有望改进情感分析和公众舆论的理解。

排序理由该集群包含一篇学术论文，详细介绍了一种新的LLM标注和编码器转移方法。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CL TIER_1 English(EN) · Maria Milkova, Maksim Rudnev · 2026-06-10 04:00

Measuring Human Value Expression in Social Media Texts: Calibrated LLM Annotation and Encoder Transfer

arXiv:2606.11018v1 Announce Type: new Abstract: Measuring subjective constructs in naturally occurring social media text requires annotation procedures that are theoretically grounded, empirically validated, and transferable to an encoder model for scalable prediction. Using non-…
arXiv cs.CL TIER_1 English(EN) · Maksim Rudnev · 2026-06-09 15:55

Measuring Human Value Expression in Social Media Texts: Calibrated LLM Annotation and Encoder Transfer

Measuring subjective constructs in naturally occurring social media text requires annotation procedures that are theoretically grounded, empirically validated, and transferable to an encoder model for scalable prediction. Using non-English social media posts annotated according t…