# Threads of Subtlety: Detecting Machine-Generated Texts Through Discourse Motifs

arXiv: https://arxiv.org/abs/2402.10586 · HTML: https://mlsanity.com/paper/2402.10586/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 60 references that are in the map.
- First posted on arXiv 16 Feb 2024.

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

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [Defending Against Neural Fake News](https://mlsanity.com/paper/1905.12616/) (2019)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer](https://mlsanity.com/paper/1803.06535/) (2018)
- [DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2306.05540/) (2023)
- [MGTBench: Benchmarking Machine-Generated Text Detection](https://mlsanity.com/paper/2303.14822/) (2023)
- [Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text](https://mlsanity.com/paper/2107.01294/) (2021)
- [OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples](https://mlsanity.com/paper/2307.11729/) (2023)
- [Real or Fake Text?: Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated Text](https://mlsanity.com/paper/2212.12672/) (2022)
- [ArguGPT: evaluating, understanding and identifying argumentative essays generated by GPT models](https://mlsanity.com/paper/2304.07666/) (2023)
- [Fighting Fire with Fire: Can ChatGPT Detect AI-generated Text?](https://mlsanity.com/paper/2308.01284/) (2023)
- [ConDA: Contrastive Domain Adaptation for AI-generated Text Detection](https://mlsanity.com/paper/2309.03992/) (2023)
- [CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Data Limitation With Contrastive Learning](https://mlsanity.com/paper/2212.10341/) (2022)
- [Distillation-Resistant Watermarking for Model Protection in NLP](https://mlsanity.com/paper/2210.03312/) (2022)
- [DMRST: A Joint Framework for Document-Level Multilingual RST Discourse Segmentation and Parsing](https://mlsanity.com/paper/2110.04518/) (2021)
- [Don't lose the message while paraphrasing: A study on content preserving style transfer](https://mlsanity.com/paper/2308.09055/) (2023)
- [Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?](https://mlsanity.com/paper/2306.05871/) (2023)
- [Does Human Collaboration Enhance the Accuracy of Identifying LLM-Generated Deepfake Texts?](https://mlsanity.com/paper/2304.01002/) (2023)
- [Is ChatGPT Involved in Texts? Measure the Polish Ratio to Detect ChatGPT-Generated Text](https://mlsanity.com/paper/2307.11380/) (2023)
- [Counter Turing Test CT^2: AI-Generated Text Detection is Not as Easy as You May Think -- Introducing AI Detectability Index](https://mlsanity.com/paper/2310.05030/) (2023)
- [Predicting Discourse Trees from Transformer-based Neural Summarizers](https://mlsanity.com/paper/2104.07058/) (2021)
- [Towards Understanding Large-Scale Discourse Structures in Pre-Trained and Fine-Tuned Language Models](https://mlsanity.com/paper/2204.04289/) (2022)

## Built on by (most cited first, 18 of 18)

- [QUDsim: Quantifying Discourse Similarities in LLM-Generated Text](https://mlsanity.com/paper/2504.09373/) (2025)
- [Is Contrasting All You Need? Contrastive Learning for the Detection and Attribution of AI-generated Text](https://mlsanity.com/paper/2407.09364/) (2024)
- [OpenTuringBench: An Open-Model-based Benchmark and Framework for Machine-Generated Text Detection and Attribution](https://mlsanity.com/paper/2504.11369/) (2025)
- [Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarization](https://mlsanity.com/paper/2502.06185/) (2025)
- [Authorship Attribution in Multilingual Machine-Generated Texts](https://mlsanity.com/paper/2508.01656/) (2025)
- [Align to Structure: Aligning Large Language Models with Structural Information](https://mlsanity.com/paper/2504.03622/) (2025)
- [Linguistic and Embedding-Based Profiling of Texts generated by Humans and Large Language Models](https://mlsanity.com/paper/2507.13614/) (2025)
- [Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models](https://mlsanity.com/paper/2504.20157/) (2025)
- [DART: An AIGT Detector using AMR of Rephrased Text](https://mlsanity.com/paper/2412.11517/) (2024)
- [Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated Text Detection](https://mlsanity.com/paper/2604.04932/) (2026)
- [Stealing Creator's Workflow: A Creator-Inspired Agentic Framework with Iterative Feedback Loop for Improved Scientific Short-form Generation](https://mlsanity.com/paper/2504.18805/) (2025)
- [Towards Structurally Explainable Machine-Generated Text Detection: A Graph-Perspective Framework](https://mlsanity.com/paper/2505.12507/) (2025)
- [SearchLLM: Detecting LLM Paraphrased Text by Measuring the Similarity with Regeneration of the Candidate Source via Search Engine](https://mlsanity.com/paper/2601.16512/) (2026)
- [Luminol-AIDetect: Fast Zero-shot Machine-Generated Text Detection based on Perplexity under Text Shuffling](https://mlsanity.com/paper/2604.25860/) (2026)
- [Hitting a Moving Target: Test-Time Adaptation for AI Text Detection under Continual Distribution Shift](https://mlsanity.com/paper/2606.25152/) (2026)
- [DiscoTrace: Representing and Comparing Answering Strategies of Humans and LLMs in Information-Seeking Question Answering](https://mlsanity.com/paper/2604.15140/) (2026)
- [Relational Over-Regularization: Graph-Based AI-Generated Text Detection via Sentence Transition Deviation](https://mlsanity.com/paper/2608.26694/) (2026)
- [D2C-Routing: Dimension-to-Composition Evidence Routing for Mixed-Origin AI-Generated Text Detection](https://mlsanity.com/paper/2608.27380/) (2026)

## Abstract (arXiv)

With the advent of large language models (LLM), the line between human-crafted and machine-generated texts has become increasingly blurred. This paper delves into the inquiry of identifying discernible and unique linguistic properties in texts that were written by humans, particularly uncovering the underlying discourse structures of texts beyond their surface structures. Introducing a novel methodology, we leverage hierarchical parse trees and recursive hypergraphs to unveil distinctive discourse patterns in texts produced by both LLMs and humans. Empirical findings demonstrate that, although both LLMs and humans generate distinct discourse patterns influenced by specific domains, human-written texts exhibit more structural variability, reflecting the nuanced nature of human writing in different domains. Notably, incorporating hierarchical discourse features enhances binary classifiers' overall performance in distinguishing between human-written and machine-generated texts, even on out-of-distribution and paraphrased samples. This underscores the significance of incorporating hierarchical discourse features in the analysis of text patterns. The code and dataset are available at https://github.com/minnesotanlp/threads-of-subtlety.