# S^2tory: Story Spine Distillation for Movie Script Summarization

arXiv: https://arxiv.org/abs/2605.03244 · HTML: https://mlsanity.com/paper/2605.03244/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 14 of 14)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [UL2: Unifying Language Learning Paradigms](https://mlsanity.com/paper/2205.05131/) (2022)
- [LongT5: Efficient Text-To-Text Transformer for Long Sequences](https://mlsanity.com/paper/2112.07916/) (2021)
- [BookSum: A Collection of Datasets for Long-form Narrative Summarization](https://mlsanity.com/paper/2105.08209/) (2021)
- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [Investigating Efficiently Extending Transformers for Long Input Summarization](https://mlsanity.com/paper/2208.04347/) (2022)
- [Select and Summarize: Scene Saliency for Movie Script Summarization](https://mlsanity.com/paper/2404.03561/) (2024)
- [EventGround: Narrative Reasoning by Grounding to Eventuality-centric Knowledge Graphs](https://mlsanity.com/paper/2404.00209/) (2024)
- [ECR-Chain: Advancing Generative Language Models to Better Emotion-Cause Reasoners through Reasoning Chains](https://mlsanity.com/paper/2405.10860/) (2024)
- [MovieSum: An Abstractive Summarization Dataset for Movie Screenplays](https://mlsanity.com/paper/2408.06281/) (2024)
- [ScreenWriter: Automatic Screenplay Generation and Movie Summarisation](https://mlsanity.com/paper/2410.19809/) (2024)
- [DiscoGraMS: Enhancing Movie Screen-Play Summarization using Movie Character-Aware Discourse Graph](https://mlsanity.com/paper/2410.14666/) (2024)

## Abstract (arXiv)

Movie scripts pose a fundamental challenge for automatic summarization due to their non-linear, cross-cut narrative structure, which makes surface-level saliency methods ineffective at preserving core story progression. To address this, we introduce S^2tory (Story Spine Distillation), a narratology-grounded framework that leverages character development trajectories to identify plot nuclei, the essential events that drive the narrative forward, while filtering out peripheral satellite events that merely enrich atmosphere or emotion. Our Narrative Expert Agent (NEAgent) performs theory-constrained reasoning, whose distilled knowledge conditions a small model to identify plot nuclei. Another model then uses these plot nuclei to generate the summary. Experiments on the MovieSum dataset demonstrate state-of-the-art semantic fidelity at approximately 3.5x compression, and zero-shot evaluation on BookSum confirms strong out-of-domain generalization. Human evaluation further validates that narratological theory provides an indispensable foundation for modeling complex, non-linear narratives.