arXiv cs.AI· Maoyuan Li, Haoyuan Li, Zhongsheng Wang, Jiamou Liu·· 12 小时前AI 评分29
研究：AI 生成辩论的价值表达丰富但组织方式不同
Value-Rich, Differently Organized: Measuring Value Expression and Organization in AI-Generated Debates
AI 导读
一项被 EMNLP 2026 主会接收的研究提出诊断性指标框架，基于 Schwartz 的 Basic-10 价值理论，从价值表达与价值组织两个维度比较人类参考辩论与 AI 生成辩论。
正文 · 原文
Abstract:Current evaluation of LLM-generated debate largely focuses on argumentative quality, leaving the value structure of generated arguments underexamined. We introduce a diagnostic metric framework for comparing how values are expressed and organized in human-reference and AI-generated debates. The framework separates value expression, the range of recognizable values a debate invokes, from value organization, how those values are distributed and sustained across turns. Grounded in Schwartz's Basic-10 value theory, it represents debates as multi-level value distributions over argumentative units, utterances, stances, and full debates, enabling metrics for value coverage, alignment, diffusion, and cross-turn dynamics. Across multiple generation systems, AI-generated debates are broadly value-expressive, often activating as many or more value dimensions than matched human references, but they organize these values differently. Their utterances are more locally value-diffuse, and source-blind judges distinguish value clarity from value focus. These findings show that debate evaluation should consider not only value presence, but also value organization. Code and supplementary materials are available at this https URL.
| Comments: | Accepted at EMNLP 2026 (Main Conference) |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.28604 [cs.AI] |
| (or arXiv:2610.28604v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28604 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Maoyuan Li [view email]
[v1]
Tue, 20 Oct 2026 17:48:56 UTC (5,026 KB)
来源：arXiv cs.AI · arxiv.org