# Artificial Text Detection via Examining the Topology of Attention Maps

arXiv: https://arxiv.org/abs/2109.04825 · HTML: https://mlsanity.com/paper/2109.04825/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 53 references that are in the map.
- First posted on arXiv 10 Sep 2021.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Are Sixteen Heads Really Better than One?](https://mlsanity.com/paper/1905.10650/) (2019)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Defending Against Neural Fake News](https://mlsanity.com/paper/1905.12616/) (2019)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [What you can cram into a single vector: Probing sentence embeddings for linguistic properties](https://mlsanity.com/paper/1805.01070/) (2018)
- [Automatic Detection of Generated Text is Easiest when Humans are Fooled](https://mlsanity.com/paper/1911.00650/) (2019)
- [Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change](https://mlsanity.com/paper/1605.09096/) (2016)
- [An introduction to Topological Data Analysis: fundamental and practical aspects for data scientists](https://mlsanity.com/paper/1710.04019/) (2017)
- [Automatic Detection of Machine Generated Text: A Critical Survey](https://mlsanity.com/paper/2011.01314/) (2020)
- [A Topological Loss Function for Deep-Learning based Image Segmentation using Persistent Homology](https://mlsanity.com/paper/1910.01877/) (2019)
- [Ripser: efficient computation of Vietoris-Rips persistence barcodes](https://mlsanity.com/paper/1908.02518/) (2019)
- [TweepFake: about Detecting Deepfake Tweets](https://mlsanity.com/paper/2008.00036/) (2020)
- [Topology of deep neural networks](https://mlsanity.com/paper/2004.06093/) (2020)
- [Real or Fake? Learning to Discriminate Machine from Human Generated Text](https://mlsanity.com/paper/1906.03351/) (2019)
- [Do Attention Heads in BERT Track Syntactic Dependencies?](https://mlsanity.com/paper/1911.12246/) (2019)
- [A Topology Layer for Machine Learning](https://mlsanity.com/paper/1905.12200/) (2019)
- [The Radicalization Risks of GPT-3 and Advanced Neural Language Models](https://mlsanity.com/paper/2009.06807/) (2020)
- [Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology](https://mlsanity.com/paper/1812.09764/) (2018)
- [Computing the Testing Error without a Testing Set](https://mlsanity.com/paper/2005.00450/) (2020)
- [Generating Sentiment-Preserving Fake Online Reviews Using Neural Language Models and Their Human- and Machine-based Detection](https://mlsanity.com/paper/1907.09177/) (2019)
- [GPU-Accelerated Computation of Vietoris-Rips Persistence Barcodes](https://mlsanity.com/paper/2003.07989/) (2020)
- [How Furiously Can Colourless Green Ideas Sleep? Sentence Acceptability in Context](https://mlsanity.com/paper/2004.00881/) (2020)
- [A Fast and Robust Method for Global Topological Functional Optimization](https://mlsanity.com/paper/2009.08496/) (2020)

## Built on by (most cited first, 30 of 49)

- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts](https://mlsanity.com/paper/2306.04723/) (2023)
- [Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods](https://mlsanity.com/paper/2210.07321/) (2022)
- [Do Language Models Plagiarize?](https://mlsanity.com/paper/2203.07618/) (2022)
- [Stylometric Detection of AI-Generated Text in Twitter Timelines](https://mlsanity.com/paper/2303.03697/) (2023)
- [Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective](https://mlsanity.com/paper/2210.10488/) (2022)
- [GPT-who: An Information Density-based Machine-Generated Text Detector](https://mlsanity.com/paper/2310.06202/) (2023)
- [Findings of the The RuATD Shared Task 2022 on Artificial Text Detection in Russian](https://mlsanity.com/paper/2206.01583/) (2022)
- [On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing](https://mlsanity.com/paper/2306.05524/) (2023)
- [Does Human Collaboration Enhance the Accuracy of Identifying LLM-Generated Deepfake Texts?](https://mlsanity.com/paper/2304.01002/) (2023)
- [To ChatGPT, or not to ChatGPT: That is the question!](https://mlsanity.com/paper/2304.01487/) (2023)
- [AI-generated text boundary detection with RoFT](https://mlsanity.com/paper/2311.08349/) (2023)
- [Acceptability Judgements via Examining the Topology of Attention Maps](https://mlsanity.com/paper/2205.09630/) (2022)
- [A Survey of AI-generated Text Forensic Systems: Detection, Attribution, and Characterization](https://mlsanity.com/paper/2403.01152/) (2024)
- [Hallucination Detection in LLMs with Topological Divergence on Attention Graphs](https://mlsanity.com/paper/2504.10063/) (2025)
- [On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook](https://mlsanity.com/paper/2307.16680/) (2023)
- [The Topological BERT: Transforming Attention into Topology for Natural Language Processing](https://mlsanity.com/paper/2206.15195/) (2022)
- [TOPFORMER: Topology-Aware Authorship Attribution of Deepfake Texts with Diverse Writing Styles](https://mlsanity.com/paper/2309.12934/) (2023)
- [Topological Data Analysis for Speech Processing](https://mlsanity.com/paper/2211.17223/) (2022)
- [An Empirical Study of AI Generated Text Detection Tools](https://mlsanity.com/paper/2310.01423/) (2023)
- [Uncertainty Estimation of Transformers' Predictions via Topological Analysis of the Attention Matrices](https://mlsanity.com/paper/2308.11295/) (2023)
- [miCSE: Mutual Information Contrastive Learning for Low-shot Sentence Embeddings](https://mlsanity.com/paper/2211.04928/) (2022)
- [BERTops: Studying BERT Representations under a Topological Lens](https://mlsanity.com/paper/2205.00953/) (2022)
- [Dialogue Term Extraction using Transfer Learning and Topological Data Analysis](https://mlsanity.com/paper/2208.10448/) (2022)
- [Can BERT eat RuCoLA? Topological Data Analysis to Explain](https://mlsanity.com/paper/2304.01680/) (2023)
- [Deciphering Textual Authenticity: A Generalized Strategy through the Lens of Large Language Semantics for Detecting Human vs. Machine-Generated Text](https://mlsanity.com/paper/2401.09407/) (2024)
- [MGT-Prism: Enhancing Domain Generalization for Machine-Generated Text Detection via Spectral Alignment](https://mlsanity.com/paper/2508.13768/) (2025)
- [Artificial Text Detection with Multiple Training Strategies](https://mlsanity.com/paper/2212.05194/) (2022)
- [Stacking the Odds: Transformer-Based Ensemble for AI-Generated Text Detection](https://mlsanity.com/paper/2310.18906/) (2023)
- [Topological Perspectives on Optimal Multimodal Embedding Spaces](https://mlsanity.com/paper/2405.18867/) (2024)

## Abstract (arXiv)

The impressive capabilities of recent generative models to create texts that are challenging to distinguish from the human-written ones can be misused for generating fake news, product reviews, and even abusive content. Despite the prominent performance of existing methods for artificial text detection, they still lack interpretability and robustness towards unseen models. To this end, we propose three novel types of interpretable topological features for this task based on Topological Data Analysis (TDA) which is currently understudied in the field of NLP. We empirically show that the features derived from the BERT model outperform count- and neural-based baselines up to 10% on three common datasets, and tend to be the most robust towards unseen GPT-style generation models as opposed to existing methods. The probing analysis of the features reveals their sensitivity to the surface and syntactic properties. The results demonstrate that TDA is a promising line with respect to NLP tasks, specifically the ones that incorporate surface and structural information.