# Storyline Trees: Hierarchical Representations for Long-Form Narratives

arXiv: https://arxiv.org/abs/2606.20900 · HTML: https://mlsanity.com/paper/2606.20900/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 63 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Builds on (most cited first, 25 of 25)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [BookSum: A Collection of Datasets for Long-form Narrative Summarization](https://mlsanity.com/paper/2105.08209/) (2021)
- [Context Length Alone Hurts LLM Performance Despite Perfect Retrieval](https://mlsanity.com/paper/2510.05381/) (2025)
- [NoLiMa: Long-Context Evaluation Beyond Literal Matching](https://mlsanity.com/paper/2502.05167/) (2025)
- [Is Semantic Chunking Worth the Computational Cost?](https://mlsanity.com/paper/2410.13070/) (2024)
- [Answer Matching Outperforms Multiple Choice for Language Model Evaluation](https://mlsanity.com/paper/2507.02856/) (2025)
- [Movie Plot Analysis via Turning Point Identification](https://mlsanity.com/paper/1908.10328/) (2019)
- [NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens](https://mlsanity.com/paper/2403.12766/) (2024)
- [QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management](https://mlsanity.com/paper/2512.12967/) (2025)
- [Reference-Guided Verdict: LLMs-as-Judges in Automatic Evaluation of Free-Form QA](https://mlsanity.com/paper/2408.09235/) (2024)
- [DetectiveQA: Evaluating Long-Context Reasoning on Detective Novels](https://mlsanity.com/paper/2409.02465/) (2024)
- [Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs](https://mlsanity.com/paper/2410.14641/) (2024)
- [Hierarchical Document Refinement for Long-context Retrieval-augmented Generation](https://mlsanity.com/paper/2505.10413/) (2025)
- [DocDancer: Towards Agentic Document-Grounded Information Seeking](https://mlsanity.com/paper/2601.05163/) (2026)
- [When Does Divide and Conquer Work for Long Context LLM? A Noise Decomposition Framework](https://mlsanity.com/paper/2506.16411/) (2025)
- [Positional Biases Shift as Inputs Approach Context Window Limits](https://mlsanity.com/paper/2508.07479/) (2025)
- [LiteraryQA: Towards Effective Evaluation of Long-document Narrative QA](https://mlsanity.com/paper/2510.13494/) (2025)
- [From Context to EDUs: Faithful and Structured Context Compression via Elementary Discourse Unit Decomposition](https://mlsanity.com/paper/2512.14244/) (2025)
- [Tree of Agents: Improving Long-Context Capabilities of Large Language Models through Multi-Perspective Reasoning](https://mlsanity.com/paper/2509.06436/) (2025)

## Abstract (arXiv)

Long-form narratives are challenging for long-context models because their structure is implicit: events, characters, and plotlines interact across hundreds of pages without the explicit cues that guide navigation in structured documents. We address this by constructing storyline trees, hierarchical representations that organize narratives from global themes and major plotlines to fine-grained events. We first segment chapters into contiguous narrative segments, or scenes, and use them as the basic units for tree construction. We then infer storyline trees through complementary top-down and bottom-up procedures that derive, refine, cluster, and summarize storylines at multiple levels of abstraction. We showcase the utility of this representation for question answering: storyline trees enable adaptive retrieval, allowing models to iteratively inspect high-level narrative structure and retrieve scene-level evidence on demand. Experiments on three long-context narrative QA benchmarks show that adaptive retrieval outperforms strong baselines, including post-trained long-context models and agentic chunk-based methods. Ablations confirm that scenes are more effective basic units than chapters or generic segmentation, and that gains persist under matched retrieval budgets