← 研踪 PaperTrailACL Anthology · ACL 2026:acl:2026.acl-srw.98 · 记录 #1
Contextual Diversity Measure (CDM) for Controllable Story Generation in Large Language Models
来源日期（仅到月份） 2026-07
来源记录日期 2026-07
雷达观测 2026-11-01 21:44
摘要
Scenario-based text generation has broad applications across education and creative writing, but remains underexplored in controllable text generation. We introduce the Contextual Diversity Measure (CDM), a metric that quantifies semantic diversity for scenario generation under fixed abstract semantic constraints, and validate it through controlled experiments. Statistical analysis across four embedding models demonstrates that CDM successfully distinguishes between high-diversity and low-diversity text pairs, with all tests achieving statistical significance at p < 0.05 on both the manually curated and LLM-generated subsets of the dataset. Effect sizes range from small-to-medium (Cohen’s d: 0.292–0.508) on the former and medium-to-large (Cohen’s d: 0.677–1.195) on the latter. Baseline comparisons indicate that CDM achieves excellent discrimination accuracy (100% and 91.9%, respectively), with discriminative power up to 5.5\times greater than the best baseline.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026-07 · 最新观测版本
Contextual Diversity Measure (CDM) for Controllable Story Generation in Large Language Models
Scenario-based text generation has broad applications across education and creative writing, but remains underexplored in controllable text generation. We introduce the Contextual Diversity Measure (CDM), a metric that quantifies semantic diversity for scenario generation under fixed abstract semantic constraints, and validate it through controlled experiments. Statistical analysis across four embedding models demonstrates that CDM successfully distinguishes between high-diversity and low-diversity text pairs, with all tests achieving statistical significance at p < 0.05 on both the manually curated and LLM-generated subsets of the dataset. Effect sizes range from small-to-medium (Cohen’s d: 0.292–0.508) on the former and medium-to-large (Cohen’s d: 0.677–1.195) on the latter. Baseline comparisons indicate that CDM achieves excellent discrimination accuracy (100% and 91.9%, respectively), with discriminative power up to 5.5\times greater than the best baseline.
查看此版本解读 →查看此版本原文 ↗