mlsanityData to 7 Oct 2026

Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution

arXiv 2607.14905 ↗First posted 16 Jul 2026cs.CL cs.AIcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Given the current trend to employ large language models (LLMs) in almost any imaginable context, LLM-generated text detection and authorship attribution have become a pressing issue. Prior work has primarily focused on surface-level linguistic features, an approach shown to be susceptible to paraphrasing and other obfuscation techniques. In this paper, we go beyond the linguistic surface, extracting and analysing reasoning structures in LLM-generated texts with the goal of capturing more complex signals of LLM authorship. We propose a graph neural network approach that leverages reasoning graphs extracted by an argument mining pipeline, demonstrating improved robustness and generalisation over a traditional Longformer baseline. Our approach outperforms the baseline by up to 27 percentage points under the obfuscation attacks such as paraphrasing and backtranslation, and 19 percentage points when evaluated on the texts generated by the unseen model versions, simulating real-world conditions in which new LLM versions are continuously released.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 31 of its 46 references that are in the map. First posted on arXiv 16 Jul 2026.

Builds on

31 of 46 references.

References · 31

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2017Graph Attention Networkscited by 8,854
  4. 2020Longformer: The Long-Document Transformercited by 3,362
  5. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  6. 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 705
  7. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 702
  8. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 500
  9. 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defensecited by 401
  10. 2023Can AI-Generated Text be Reliably Detected?cited by 372
  11. 2024Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Textcited by 255
  12. 2024RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectorscited by 157
19 more
  1. 2020The Tatoeba Translation Challenge -- Realistic Data Sets for Low Resource and Multilingual MTcited by 127
  2. 2023DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Textcited by 127
  3. 2024Measuring Political Bias in Large Language Models: What Is Said and How It Is Saidcited by 89
  4. 2024Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challengescited by 46
  5. 2023ArguGPT: evaluating, understanding and identifying argumentative essays generated by GPT modelscited by 41
  6. 2022Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspectivecited by 40
  7. 2023Origin Tracing and Detecting of LLMscited by 39
  8. 2024Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Mediacited by 35
  9. 2024Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attackcited by 27
  10. 2020Transformer-Based Models for Automatic Identification of Argument Relations: A Cross-Domain Evaluationcited by 20
  11. 2022Automatic Debate Evaluation with Argumentation Semantics and Natural Language Argument Graph Networkscited by 10
  12. 2025Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectorscited by 10
  13. 2024RAFT: Realistic Attacks to Fool Text Detectorscited by 8
  14. 2024ESPERANTO: Evaluating Synthesized Phrases to Enhance Robustness in AI Detection for Text Originationcited by 6
  15. 2026The Impact of AI-Generated Text on the Internetcited by 6
  16. 2024NLAS-multi: A Multilingual Corpus of Automatically Generated Natural Language Argumentation Schemescited by 5
  17. 2021Tree-Constrained Graph Neural Networks For Argument Miningcited by 2
  18. 2024Navigating the Shadows: Unveiling Effective Disturbances for Modern AI Content Detectorscited by 2
  19. 2025Heterogeneous Graph Neural Networks for Assumption-Based Argumentationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Can Large Language Models Identify Authorship?
  2. 2024A Bayesian Approach to Harnessing the Power of LLMs in Authorship Attribution
  3. 2025Actions Speak Louder than Prompts: A Large-Scale Study of LLMs for Graph Inference
  4. 2023Large Language Models on Graphs: A Comprehensive Survey
  5. 2025The Erosion of LLM Signatures: Can We Still Distinguish Human and LLM-Generated Scientific Ideas After Iterative Paraphrasing?
  6. 2026Detecting Data Contamination in Large Language Models
  7. 2025KG-LLM-Bench: A Scalable Benchmark for Evaluating LLM Reasoning on Textualized Knowledge Graphs
  8. 2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs