arXiv Computation and Language September 1, 2026 By Gaspard Michel, Elena V. Epure, Romain Hennequin, Christophe Cerisara, Mirella Lapata

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

Read the original on arXiv Computation and Language →

GraphLit introduces Dynamic Heterogeneous Character Networks (DHCNs) that structure long novels into temporally localized graphs aligning characters with their textual contexts. Using a masked graph autoencoder, GraphLit learns rich literary representations and outperforms text-only, graph-only, and prior hybrid baselines on 12 character-related tasks. Ablation studies show that grounding characters in context is the primary performance driver, while narrative order and character relationships offer task-dependent gains, and the framework is applied to analyze the link between narrative non-linearity and dynamic social features.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Jul 24

Semi-Supervised Text-Attributed Graph Distillation

arXiv:2607. 20477v1 Announce Type: new Abstract: {\em Text-Attributed Graphs} (TAGs) have emerged as an expressive data model for integrating graph topology with rich textual semantics.

By Yurui Lai, Samir Moustafa, Renchi Yang, Tsz Nam Chan

llms efficiency benchmarks

arXiv AI

Jul 2

AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation

arXiv:2607. 00052v1 Announce Type: cross Abstract: GraphRAG is an extension of retrieval-augmented generation (RAG) that supports large language models (LLMs) by referring to graph-structured data as external knowledge.

By Bao Long Nguyen Huu, Atsushi Hashimoto

llms rag benchmarks

arXiv AI

6d ago

Critic's Eye: Review-Grounded Graph Reasoning for Long-Form Motif Discovery

The paper introduces Critic's Eye, a method for computational motif discovery that models a play as a heterogeneous Narrative Topology Graph and performs discriminative inference over global structural evidence. It achieves 84.8% Hit@5 on a benchmark, nearly quadrupling the performance of large foundation models such as Gemini-3-pro-preview. The authors argue that explicit structural priors outperform mere parameter scaling for decoding the complex architecture of long‑form literature.

By Xinyu Sun, Zhangyue Yin, Xinyi Ju, Xin Wang

llms benchmarks safety

arXiv AI

Sep 10

Beyond Sparse Rewards: A New Benchmark and Structure-Aware Graph Alignment for Micro-Drama Understanding

arXiv:2609.07107v1 Announce Type: new Abstract: Micro-dramas, characterized by ultra-short durations and hyper-dense storylines, pose unique challenges for video understanding that conventional bench...

By Yixin Qin, Shi-Zhe Chen, Zhiqi Yu, Siyuan Cheng, Tao Cheng, Jinwen Luo, Zheng Wei

reinforcement-learning benchmarks safety

arXiv AI

Jun 11

MLaGA: Multimodal Large Language and Graph Assistant

arXiv:2506. 02568v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated substantial efficacy in advancing graph-structured data analysis.

By Dongzhe Fan, Yi Fang, Jiajin Liu, Djellel Difallah, Qiaoyu Tan

llms fine-tuning multimodal

arXiv Machine Learning

Jul 1

TAG-DLM: Diffusion Language Models for Text-Attributed Graph Learning

arXiv:2606. 31166v1 Announce Type: cross Abstract: Text-attributed graphs (TAGs), where each node carries a natural language description, require models to jointly reason over text and graph topology.

By Lingjie Chen, Yuanchen Bei, Haobo Xu, Yanjun Zhao, Yuzhong Chen, Hanghang Tong

llms diffusion fine-tuning benchmarks

One email a morning, machine-written

Related stories

Semi-Supervised Text-Attributed Graph Distillation

AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation

Critic's Eye: Review-Grounded Graph Reasoning for Long-Form Motif Discovery

Beyond Sparse Rewards: A New Benchmark and Structure-Aware Graph Alignment for Micro-Drama Understanding

MLaGA: Multimodal Large Language and Graph Assistant

TAG-DLM: Diffusion Language Models for Text-Attributed Graph Learning