arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.05052cs.CLcs.AIcs.CYcs.LG
收藏

超越独立标签:用于人类价值检测的施瓦茨几何解码

Beyond Independent Labels: Schwartz-Geometry Decoding for Human Value Detection

PRHLT Research Center, Universitat Politècnica de València(PRHLT研究中心,瓦伦西亚理工大学);School of Science, Engineering and Design, Universidad Europea de Valencia(科学、工程与设计学院,欧洲瓦伦西亚大学);Valencian Graduate School and Research Network of Artificial Intelligence (ValgrAI)(瓦伦西亚人工智能研究生学院及研究网络)

Víctor Yeste, Paolo Rosso

AI总结:

研究人类价值检测问题,对比两种注入施瓦茨理论结构的方式,发现训练时几何感知目标增益有限,后验施瓦茨感知能量解码器可使标签集与连续统更一致且不影响宏观和微观F1值。

摘要:

人类价值检测通常被表述为对19个细化的施瓦茨值进行句子级多标签分类,通常预测为独立标签。然而,施瓦茨理论将它们描述为一个循环动机连续统,其中相邻值兼容,相反值相互矛盾。我们探讨这种结构是否可以作为显式输出空间几何来操作,并用作软偏差而非硬约束。在DeBERTa-v3-base分类器上,我们比较了两种注入方式:训练时几何感知目标和事后施瓦茨感知能量解码器,后者对整个标签集进行联合评分。在五个种子上,训练时几何仅带来有限增益——对于真实连续统并不比随机排序更大——而解码器使标签集在我们引入的理论感知一致性度量上与连续统更一致,且对宏观F1或微观F1没有成本(由其选择规则保持固定)。增益特定于真实的施瓦茨排序:通过相同解码器,对于随机排列或经验共现图不会出现。有界的Qwen2.5-72B-Instruct诊断表明,在推理时提供连续统会改变行为,但与监督结构化预测不匹配。因此,理论感知解码提供了一种轻量级、可控的方法,使价值检测忠实于其标签空间。

英文摘要:

Human value detection is commonly formulated as sentence-level multi-label classification over the 19 refined Schwartz values, typically predicted as independent labels. Schwartz theory, however, describes them as a circular motivational continuum, in which adjacent values are compatible and opposing values are in tension. We ask whether this structure can be operationalized as an explicit output-space geometry and used as a soft bias rather than a hard constraint. On a DeBERTa-v3-base classifier, we compare two ways of injecting it: training-time geometry-aware objectives and a post-hoc Schwartz-aware energy decoder that scores whole label sets jointly. Across five seeds, training-time geometry gives only limited gains-no larger for the true continuum than for a random ordering-whereas the decoder makes label sets more coherent with the continuum-on theory-aware coherence metrics we introduce-at no cost to Macro-F1 or Micro-F1 (held fixed by its selection rule). The gain is specific to the true Schwartz ordering: it does not appear for a random permutation or an empirical co-occurrence graph through the identical decoder. A bounded Qwen2.5-72B-Instruct diagnostic shows that supplying the continuum at inference shifts behavior but does not match supervised structured prediction. Theory-aware decoding thus offers a lightweight, controllable way to make value detection faithful to its label space.

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。

↑