# HULLMI: Human vs LLM identification with explainability

arXiv: https://arxiv.org/abs/2409.04808 · HTML: https://mlsanity.com/paper/2409.04808/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 41 references that are in the map.
- First posted on arXiv 7 Sep 2024.

## Builds on (most cited first, 22 of 22)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [RADAR: Robust AI-Text Detection via Adversarial Learning](https://mlsanity.com/paper/2307.03838/) (2023)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [Automatic Detection of Machine Generated Text: A Critical Survey](https://mlsanity.com/paper/2011.01314/) (2020)
- [In-Context Impersonation Reveals Large Language Models' Strengths and Biases](https://mlsanity.com/paper/2305.14930/) (2023)
- [Large Language Models for Cyber Security: A Systematic Literature Review](https://mlsanity.com/paper/2405.04760/) (2024)
- [Stylometric Detection of AI-Generated Text in Twitter Timelines](https://mlsanity.com/paper/2303.03697/) (2023)
- [LLM-as-a-Coauthor: Can Mixed Human-Written and Machine-Generated Text Be Detected?](https://mlsanity.com/paper/2401.05952/) (2024)
- [GPT-Sentinel: Distinguishing Human and ChatGPT Generated Content](https://mlsanity.com/paper/2305.07969/) (2023)
- [Large Language Models in Cybersecurity: State-of-the-Art](https://mlsanity.com/paper/2402.00891/) (2024)
- [Assessing Political Bias in Large Language Models](https://mlsanity.com/paper/2405.13041/) (2024)
- [Detecting AI-Generated Text: Factors Influencing Detectability with Current Methods](https://mlsanity.com/paper/2406.15583/) (2024)
- [ChatGPT: More than a Weapon of Mass Deception, Ethical challenges and responses from the Human-Centered Artificial Intelligence (HCAI) perspective](https://mlsanity.com/paper/2304.11215/) (2023)
- [Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Text](https://mlsanity.com/paper/2403.05750/) (2024)
- [LLM-Detector: Improving AI-Generated Chinese Text Detection with Open-Source LLM Instruction Tuning](https://mlsanity.com/paper/2402.01158/) (2024)
- [Enhancing Text Authenticity: A Novel Hybrid Approach for AI-Generated Text Detection](https://mlsanity.com/paper/2406.06558/) (2024)
- [The Impact of Prompts on Zero-Shot Detection of AI-Generated Text](https://mlsanity.com/paper/2403.20127/) (2024)
- [Differentiating Between Human-Written and AI-Generated Texts Using Automatically Extracted Linguistic Features](https://mlsanity.com/paper/2407.03646/) (2024)
- [Fake News Detection: It's All in the Data!](https://mlsanity.com/paper/2407.02122/) (2024)

## Built on by (most cited first, 3 of 3)

- [Visual Error Patterns in Multi-Modal AI: A Statistical Approach](https://mlsanity.com/paper/2412.00083/) (2024)
- [READER: Reasoning-Enhanced AI-Generated Text Detection](https://mlsanity.com/paper/2605.25281/) (2026)
- [DeBERTa-Sentinel: Toward Transparent and Trustworthy Detection of AI-Generated Text](https://mlsanity.com/paper/2608.01046/) (2026)

## Abstract (arXiv)

As LLMs become increasingly proficient at producing human-like responses, there has been a rise of academic and industrial pursuits dedicated to flagging a given piece of text as "human" or "AI". Most of these pursuits involve modern NLP detectors like T5-Sentinel and RoBERTa-Sentinel, without paying too much attention to issues of interpretability and explainability of these models. In our study, we provide a comprehensive analysis that shows that traditional ML models (Naive-Bayes,MLP, Random Forests, XGBoost) perform as well as modern NLP detectors, in human vs AI text detection. We achieve this by implementing a robust testing procedure on diverse datasets, including curated corpora and real-world samples. Subsequently, by employing the explainable AI technique LIME, we uncover parts of the input that contribute most to the prediction of each model, providing insights into the detection process. Our study contributes to the growing need for developing production-level LLM detection tools, which can leverage a wide range of traditional as well as modern NLP detectors we propose. Finally, the LIME techniques we demonstrate also have the potential to equip these detection tools with interpretability analysis features, making them more reliable and trustworthy in various domains like education, healthcare, and media.