arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.01976cs.CL
收藏

Taking a SEAT:基于情感、情绪、论证与主题标注预测价值解读

Taking a SEAT: Predicting Value Interpretations from Sentiment, Emotion, Argument, and Topic Annotations

Delft University of Technology(代尔夫特理工大学)

Adina Nicola Dobrinoiu, Ana Cristiana Marcu, Amir Homayounirad, Luciano Cavalcante Siebert, Enrico Liscio

AI总结:

本研究提出利用情感、情绪、论证与主题(SEAT)多维度主观标注作为代理,让语言模型预测个体价值解读,实验证实多维度结合效果更优,为后续相关研究奠定基础。

摘要:

我们对价值概念的解读受社会文化背景与生活经历塑造,因此具有主观性。识别个体的价值解读对于开发能契合多元人类视角、避免偏向多数群体观点的AI系统至关重要。为此,我们探究语言模型能否借助多维度主观标注作为个体解读视角的代理,来预测个体的价值解读。具体而言,我们评估向语言模型提供个体对情感(Sentiment)、情绪(Emotion)、论证(Argument)与主题(Topics,即SEAT维度)的标注示例,是否有助于模型预测该个体的价值解读。我们在不同零样本与少样本设置下开展的实验表明,同时提供全部SEAT维度的信息,其表现优于仅提供单个维度的情况,也优于不提供任何个体信息的基线。此外,标注者之间的个体差异凸显了纳入个体主观标注者特征的重要性。据我们所知,这种受控设置尽管规模较小,却是首次超越人口统计学范畴、探究标注行为对价值预测影响的尝试,为未来的大规模验证奠定了坚实基础。

英文摘要:

Our interpretation of value concepts is shaped by our sociocultural background and lived experiences, and is thus subjective. Recognizing individual value interpretations is important for developing AI systems that can align with diverse human perspectives and avoid bias toward majority viewpoints. To this end, we investigate whether a language model can predict individual value interpretations by leveraging multi-dimensional subjective annotations as a proxy for their interpretive lens. That is, we evaluate whether providing examples of how an individual annotates Sentiment, Emotion, Argument, and Topics (SEAT dimensions) helps a language model in predicting their value interpretations. Our experiment across different zero- and few-shot settings demonstrates that providing all SEAT dimensions simultaneously yields superior performance compared to individual dimensions and a baseline where no information about the individual is provided. Furthermore, individual variations across annotators highlight the importance of accounting for the incorporation of individual subjective annotators. To the best of our knowledge, this controlled setting, although small in size, is the first attempt to go beyond demographics and investigate the impact of annotation behavior on value prediction, providing a solid foundation for future large-scale validation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑