# When Large Language Models Do Not Work: Online Incivility Prediction through Graph Neural Networks

arXiv: https://arxiv.org/abs/2512.07684 · HTML: https://mlsanity.com/paper/2512.07684/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 8 Dec 2025.

## Builds on (most cited first, 13 of 13)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/1809.05679/) (2018)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- [ChatGPT Informed Graph Neural Network for Stock Movement Prediction](https://mlsanity.com/paper/2306.03763/) (2023)
- [CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Reward](https://mlsanity.com/paper/2504.03724/) (2025)
- [Benchmarking Large Language Models for Image Classification of Marine Mammals](https://mlsanity.com/paper/2410.19848/) (2024)
- [Modeling Inverse Demand Function with Explainable Dual Neural Networks](https://mlsanity.com/paper/2307.14322/) (2023)
- [Stand for Something or Fall for Everything: Predict Misinformation Spread with Stance-Aware Graph Neural Networks](https://mlsanity.com/paper/2310.02568/) (2023)
- [Tiny-Toxic-Detector: A compact transformer-based model for toxic content detection](https://mlsanity.com/paper/2409.02114/) (2024)

## Abstract (arXiv)

Online incivility has emerged as a widespread and persistent problem in digital communities, imposing substantial social and psychological burdens on users. Although many platforms attempt to curb incivility through moderation and automated detection, the performance of existing approaches often remains limited in both accuracy and efficiency. To address this challenge, we propose a Graph Neural Network (GNN) framework for detecting three types of uncivil behavior (i.e., toxicity, aggression, and personal attacks) within the English Wikipedia community. Our model represents each user comment as a node, with textual similarity between comments defining the edges, allowing the network to jointly learn from both linguistic content and relational structures among comments. We also introduce a dynamically adjusted attention mechanism that adaptively balances nodal and topological features during information aggregation. Empirical evaluations demonstrate that our proposed architecture outperforms 12 state-of-the-art Large Language Models (LLMs) across multiple metrics while requiring significantly lower inference cost. These findings highlight the crucial role of structural context in detecting online incivility and address the limitations of text-only LLM paradigms in behavioral prediction. All datasets and comparative outputs will be publicly available in our repository to support further research and reproducibility.