Awesome World Model Hub Papers · Datasets · Projects
← Back to datasets

NarrativeWorldBench

2026 Datasets
Preview for NarrativeWorldBench

Dataset Analysis

Introduces a benchmark and latent world model for long-horizon co-creative audio drama, outperforming frontier LLMs in consistency and controllability.

Provenance

Collected from papers.

Derived from paper: NarrativeWorldBench: A Frontier-Saturated Benchmark and a Latent World Model for Long-Horizon Co-Creative Audio Drama

Resources

Tags

audio dramalong-horizonbenchmarknarrative understandingstate-space modelLLM evaluationCLAI