Search papers, labs, and topics across Lattice.
The paper introduces PLOTTER, a framework for narrative generation that plans on structural graph representations of events and characters instead of directly on text. PLOTTER uses an Evaluate-Plan-Revise cycle on these graphs, optimizing causality and narrative structure under logical constraints before generating the full narrative. Experiments show PLOTTER significantly outperforms baselines, demonstrating the importance of graph-based planning for long-context reasoning in complex narrative generation.
LLMs can write better stories if they plan the plot on a graph first.
While LLMs demonstrate remarkable fluency in narrative generation, existing methods struggle to maintain global narrative coherence, contextual logical consistency, and smooth character development, often producing monotonous scripts with structural fractures. To this end, we introduce PLOTTER, a framework that performs narrative planning on structural graph representations instead of the direct sequential text representations used in existing work. Specifically, PLOTTER executes the Evaluate-Plan-Revise cycle on the event graph and character graph. By diagnosing and repairing issues of the graph topology under rigorous logical constraints, the model optimizes the causality and narrative skeleton before complete context generation. Experiments demonstrate that PLOTTER significantly outperforms representative baselines across diverse narrative scenarios. These findings verify that planning narratives on structural graph representations-rather than directly on text-is crucial to enhance the long context reasoning of LLMs in complex narrative generation.
