Contextual Diversity Measure (CDM) for Controllable Story Generation in Large Language Models

ACL ARR 2026 January Submission4568 Authors

Keywords: Diversity Measure, Controllable Story Generation, Scenario text generation

Abstract: Scenario-based text generation has broad applications across education and creative writing, but remains underexplored in the controllable text generation problem domain. We introduce the Contextual Diversity Measure (CDM), a metric that quantifies semantic diversity for scenario generation given abstract semantic role labeling 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 significance at $p < 0.05$ and small-to-medium effect sizes (Cohen's $d$ from 0.292 to 0.508). Baseline comparisons show that CDM achieves perfect discrimination accuracy (100\%) with the best-performing variant producing a discriminative power $1.5\times$ greater than the best baseline.

Paper Type: Long

Research Area: Semantics: Lexical, Sentence-level Semantics, Textual Inference and Other areas

Research Area Keywords: Semantics: Lexical and Sentence-Level

Contribution Types: Model analysis & interpretability, Data analysis, Theory

Languages Studied: English

Submission Number: 4568