# Detecting AI-Generated Texts in Cross-Domains

arXiv: https://arxiv.org/abs/2410.13966 · HTML: https://mlsanity.com/paper/2410.13966/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 17 Oct 2024.

## Builds on (most cited first, 9 of 9)

- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation](https://mlsanity.com/paper/2109.13296/) (2021)
- [TweepFake: about Detecting Deepfake Tweets](https://mlsanity.com/paper/2008.00036/) (2020)
- [Unsupervised and Distributional Detection of Machine-Generated Text](https://mlsanity.com/paper/2111.02878/) (2021)
- [Beyond Black Box AI-Generated Plagiarism Detection: From Sentence to Document Level](https://mlsanity.com/paper/2306.08122/) (2023)
- [Content Significance Distribution of Sub-Text Blocks in Articles and Its Application to Article-Organization Assessment](https://mlsanity.com/paper/2311.01673/) (2023)

## Built on by (most cited first, 2 of 2)

- [Understanding the Effects of RLHF on the Quality and Detectability of LLM-Generated Texts](https://mlsanity.com/paper/2503.17965/) (2025)
- [Sentence Specificity Scores for Collaborative Technical Documentation: A Domain-Transfer Study](https://mlsanity.com/paper/2610.01046/) (2026)

## Abstract (arXiv)

Existing tools to detect text generated by a large language model (LLM) have met with certain success, but their performance can drop when dealing with texts in new domains. To tackle this issue, we train a ranking classifier called RoBERTa-Ranker, a modified version of RoBERTa, as a baseline model using a dataset we constructed that includes a wider variety of texts written by humans and generated by various LLMs. We then present a method to fine-tune RoBERTa-Ranker that requires only a small amount of labeled data in a new domain. Experiments show that this fine-tuned domain-aware model outperforms the popular DetectGPT and GPTZero on both in-domain and cross-domain texts, where AI-generated texts may either be in a different domain or generated by a different LLM not used to generate the training datasets. This approach makes it feasible and economical to build a single system to detect AI-generated texts across various domains.