GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study
cs.CL
Submitted: 2026-05-27
Updated: 2026-08-31
Comments: EMNLP 2026 (Main)
Code: https://github.com/gasmichel/GraphLit
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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
Terminology
Abstract
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.
Sources
- Mining and modeling character networks
- Heterogeneous Graph Transformer
- Variational Graph Auto-Encoders
- The NarrativeQA Reading Comprehension Challenge
- LongBench Pro: A More Realistic and Comprehensive Bilingual Long-Context Evaluation Benchmark
- The Llama 3 Herd of Models
- Computational Representations of Character Significance in Novels
- One Graph to Rule them All: Using NLP and Graph Neural Networks to analyse Tolkien's Legendarium
- Attention Is All You Need
- Multilingual E5 Text Embeddings: A Technical Report
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering