Automatic story generation aims to produce coherent, engaging, and contextually consistent narratives with minimal or no human involvement, thereby advancing research in computational creativity and applications in human language technologies. The emergence of large language models has progressed the task, enabling systems to generate multi-thousand-word stories under diverse constraints. Despite these advances, maintaining narrative coherence, character consistency, storyline diversity, and plot controllability in generating stories is still challenging. In this survey, we conduct a systematic review of research published over the past four years to examine the major trends and key limitations in story generation methods, model architectures, datasets, and evaluation methodologies. Based on this analysis of 57 included papers, we propose developing new evaluation metrics and creating more suitable datasets, together with ongoing improvement of narrative coherence and consistency, as well as their exploration in practical applications of story generation, as actions to support continued progress in automatic story generation.

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× greater than the best baseline.