# Leveraging Explainable AI for LLM Text Attribution: Differentiating Human-Written and Multiple LLMs-Generated Text

arXiv: https://arxiv.org/abs/2501.03212 · HTML: https://mlsanity.com/paper/2501.03212/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 34 references that are in the map.
- First posted on arXiv 6 Jan 2025.

## Builds on (most cited first, 8 of 8)

- [Using an LLM to Help With Code Understanding](https://mlsanity.com/paper/2307.08177/) (2023)
- [The Science of Detecting LLM-Generated Texts](https://mlsanity.com/paper/2303.07205/) (2023)
- [Detecting LLM-Generated Text in Computing Education: A Comparative Study for ChatGPT Cases](https://mlsanity.com/paper/2307.07411/) (2023)
- [Data Race Detection Using Large Language Models](https://mlsanity.com/paper/2308.07505/) (2023)
- [The Imitation Game: Detecting Human and AI-Generated Texts in the Era of ChatGPT and BARD](https://mlsanity.com/paper/2307.12166/) (2023)
- [Question-Answering (QA) Model for a Personalized Learning Assistant for Arabic Language](https://mlsanity.com/paper/2406.08519/) (2024)
- [Transformer Models in Education: Summarizing Science Textbooks with AraBART, MT5, AraT5, and mBART](https://mlsanity.com/paper/2406.07692/) (2024)
- [Automated Question Generation for Science Tests in Arabic Language Using NLP Techniques](https://mlsanity.com/paper/2406.08520/) (2024)

## Built on by (most cited first, 11 of 11)

- [Benchmarking the Detection of LLMs-Generated Modern Chinese Poetry](https://mlsanity.com/paper/2509.01620/) (2025)
- [StoryScope: Investigating idiosyncrasies in AI fiction](https://mlsanity.com/paper/2604.03136/) (2026)
- [E-PhishGen: Unlocking Novel Research in Phishing Email Detection](https://mlsanity.com/paper/2509.01791/) (2025)
- [The Attribution Crisis in LLM Search Results](https://mlsanity.com/paper/2508.00838/) (2025)
- [Why AI-Generated Text Detection Fails: Evidence from Explainable AI Beyond Benchmark Accuracy](https://mlsanity.com/paper/2603.23146/) (2026)
- [Seeing the Poem: Image-Semantic Detection of AI-Generated Modern Chinese Poetry with MLLMs](https://mlsanity.com/paper/2605.22654/) (2026)
- [When New Generators Arrive: Lifelong Machine-Generated Text Attribution via Ridge Feature Transfer](https://mlsanity.com/paper/2606.05626/) (2026)
- [Distinguishing Artificial from Authentic: Evaluating LLMs for Detecting LLM-Generated Content](https://mlsanity.com/paper/2607.20446/) (2026)
- [LLM Agents Make Collective Belief Dynamics Programmable: Challenges and Research Directions](https://mlsanity.com/paper/2605.19915/) (2026)
- [Show, Don't TELL: Explainable AI-Generated Text Detection](https://mlsanity.com/paper/2605.27921/) (2026)
- [CASPER in the Machine: Insights into Character Variety in LLM-Generated Stories](https://mlsanity.com/paper/2606.22454/) (2026)

## Abstract (arXiv)

The development of Generative AI Large Language Models (LLMs) raised the alarm regarding identifying content produced through generative AI or humans. In one case, issues arise when students heavily rely on such tools in a manner that can affect the development of their writing or coding skills. Other issues of plagiarism also apply. This study aims to support efforts to detect and identify textual content generated using LLM tools. We hypothesize that LLMs-generated text is detectable by machine learning (ML), and investigate ML models that can recognize and differentiate texts generated by multiple LLMs tools. We leverage several ML and Deep Learning (DL) algorithms such as Random Forest (RF), and Recurrent Neural Networks (RNN), and utilized Explainable Artificial Intelligence (XAI) to understand the important features in attribution. Our method is divided into 1) binary classification to differentiate between human-written and AI-text, and 2) multi classification, to differentiate between human-written text and the text generated by the five different LLM tools (ChatGPT, LLaMA, Google Bard, Claude, and Perplexity). Results show high accuracy in the multi and binary classification. Our model outperformed GPTZero with 98.5% accuracy to 78.3%. Notably, GPTZero was unable to recognize about 4.2% of the observations, but our model was able to recognize the complete test dataset. XAI results showed that understanding feature importance across different classes enables detailed author/source profiles. Further, aiding in attribution and supporting plagiarism detection by highlighting unique stylistic and structural elements ensuring robust content originality verification.