用情绪强度分析大模型对后苏联地区表述差异，发现传统情感分析遗漏关键维度。
REGARD: Regional Affective Differences in Large Language Models
- 通过情绪三维度（效价-唤醒-支配）量化模型对500个区域目标的表述
- 19个模型分三类，低唤醒模型倾向用模板回避评价性问题
- 揭示了传统正负情感分析无法捕捉的情绪强度差异
在不同语言和区域生态中训练与对齐的大语言模型，可能以不同方式描述同一政治、文化及地缘政治实体。现有评估多依赖情感、好感度或立场，将模型态度简化为单一正负轴。本文提出REGARD，通过目标导向的效价-唤醒-支配（VAD）分析，研究大模型对后苏联地区实体的语义情感差异。我们向19个模型提问500个区域特定目标，由GPT-4o-mini和Qwen3.6-35B-A3B两个独立大模型评分，并在300项人工标注子集上验证测量结果。基于情绪特征与响应行为的层次聚类（Ward-linkage）将所有模型分为三类，该分类跨越模型来源、家族和参数量。通用回答率与低唤醒显著相关（r = -0.81），使用模板回避评价的模型无论来源如何，均聚集于低唤醒组。结果表明，VAD分析可捕捉传统情感评估忽略的情绪强度维度。
原文摘要 · Abstract (English)
Large language models trained and aligned within different linguistic and regional ecosystems may frame the same political, cultural, and geopolitical entities in different ways. Such differences are often evaluated through sentiment, favorability, or stance, reducing model attitudes to a single positive-negative axis. We introduce REGARD, a study of what drives affective framing differences across LLMs on post-Soviet entities using target-directed Valence-Arousal-Dominance profiling. We query 19 models on 500 region-specific targets, score their responses with two independent LLM judges, GPT-4o-mini and Qwen3.6-35B-A3B, and validate the measurements on a 300-item human-annotated subset. Post-hoc Ward-linkage clustering of all 19 models by affective and response-behavior profiles yields three behavioral clusters that cut across model origin, family, and parameter count. Generic-answer rate is strongly associated with lower arousal (r = -0.81) and with cluster placement: models that deflect evaluative prompts with templated responses cluster together at low arousal regardless of origin. These findings show that VAD profiling captures emotional intensity, a dimension of affective framing that is largely invisible to conventional sentiment-based evaluation.
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。