# GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study

arXiv: https://arxiv.org/abs/2605.28643 · HTML: https://mlsanity.com/paper/2605.28643/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 68 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [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)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4](https://mlsanity.com/paper/2305.00118/) (2023)
- ["Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding](https://mlsanity.com/paper/2109.05438/) (2021)
- [Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works](https://mlsanity.com/paper/2404.12726/) (2024)
- [Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks](https://mlsanity.com/paper/2404.06480/) (2024)
- [Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data](https://mlsanity.com/paper/2205.07557/) (2022)
- [LongBench Pro: A More Realistic and Comprehensive Bilingual Long-Context Evaluation Benchmark](https://mlsanity.com/paper/2601.02872/) (2026)
- [Multi-level Contrastive Learning for Script-based Character Understanding](https://mlsanity.com/paper/2310.13231/) (2023)
- [The Project Dialogism Novel Corpus: A Dataset for Quotation Attribution in Literary Texts](https://mlsanity.com/paper/2204.05836/) (2022)
- [NarraBench: A Comprehensive Framework for Narrative Benchmarking](https://mlsanity.com/paper/2510.09869/) (2025)
- [Fine-Grained Modeling of Narrative Context: A Coherence Perspective via Retrospective Questions](https://mlsanity.com/paper/2402.13551/) (2024)
- [Improving Automatic Quotation Attribution in Literary Novels](https://mlsanity.com/paper/2307.03734/) (2023)
- [CHIRON: Rich Character Representations in Long-Form Narratives](https://mlsanity.com/paper/2406.10190/) (2024)
- [Mining and modeling character networks](https://mlsanity.com/paper/1608.00646/) (2016)
- [Improving Quotation Attribution with Fictional Character Embeddings](https://mlsanity.com/paper/2406.11368/) (2024)
- [Renard: A Modular Pipeline for Extracting Character Networks from Narrative Texts](https://mlsanity.com/paper/2407.02284/) (2024)
- [Evaluating Computational Representations of Character: An Austen Character Similarity Benchmark](https://mlsanity.com/paper/2408.16131/) (2024)
- [BookWorm: A Dataset for Character Description and Analysis](https://mlsanity.com/paper/2410.10372/) (2024)
- [The Role of Natural Language Processing Tasks in Automatic Literary Character Network Construction](https://mlsanity.com/paper/2412.11560/) (2024)
- [BOOKCOREF: Coreference Resolution at Book Scale](https://mlsanity.com/paper/2507.12075/) (2025)
- [Temporal Network Analysis of Literary Texts](https://mlsanity.com/paper/1602.07275/) (2016)

## Built on by (most cited first, 1 of 1)

- [Fast and Accurate Quotation Attribution in Literary Texts](https://mlsanity.com/paper/2608.02359/) (2026)

## Abstract (arXiv)

Methods to represent literary texts as graphs or sequences of graphs mainly focus on representing character interactions, and often overlook another crucial aspect: the textual context in which characters interact. We introduce Dynamic Heterogeneous Character Networks (DHCNs), which organize long novels into temporally localized heterogeneous graphs that align characters with their textual contexts. We extract around 20,000 DHCNs from Project Gutenberg, and propose GraphLit, a self-supervised learning framework that learns rich literary representations through a masked graph autoencoder objective. Across a wide range of 12 character-related tasks, GraphLit improves over text-only, graph-only and prior hybrid baselines. Ablations over different kinds of dynamic graph structures and architectural elements show that grounding characters in their context is the main performance driver, while explicitly encoding narrative order and character relationships provide task-dependent improvements. Finally, we demonstrate the applicability of DHCNs and GraphLit for literary analysis by studying the link between narrative non-linearity and dynamic social features.