# Learning to Rewrite: Generalized LLM-Generated Text Detection

arXiv: https://arxiv.org/abs/2408.04237 · HTML: https://mlsanity.com/paper/2408.04237/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 8 Aug 2024.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [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)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Defending Against Neural Fake News](https://mlsanity.com/paper/1905.12616/) (2019)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [The Curse of Recursion: Training on Generated Data Makes Models Forget](https://mlsanity.com/paper/2305.17493/) (2023)
- [Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature](https://mlsanity.com/paper/2310.05130/) (2023)
- [DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2306.05540/) (2023)
- [TweepFake: about Detecting Deepfake Tweets](https://mlsanity.com/paper/2008.00036/) (2020)
- [From Amateurs to Connoisseurs: Modeling the Evolution of User Expertise through Online Reviews](https://mlsanity.com/paper/1303.4402/) (2013)
- [ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Text](https://mlsanity.com/paper/2301.13852/) (2023)
- [Raidar: geneRative AI Detection viA Rewriting](https://mlsanity.com/paper/2401.12970/) (2024)
- [Towards Answering Climate Questionnaires from Unstructured Climate Reports](https://mlsanity.com/paper/2301.04253/) (2023)

## Built on by (most cited first, 13 of 13)

- [Practical Poisoning Attacks against Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.03957/) (2025)
- [Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text](https://mlsanity.com/paper/2601.21895/) (2026)
- [Not all tokens are created equal: Perplexity Attention Weighted Networks for AI generated text detection](https://mlsanity.com/paper/2501.03940/) (2025)
- [ConspEmoLLM-v2: A robust and stable model to detect sentiment-transformed conspiracy theories](https://mlsanity.com/paper/2505.14917/) (2025)
- [Learning to Rewrite Prompts for Bootstrapping LLMs on Downstream Tasks](https://mlsanity.com/paper/2510.06695/) (2025)
- [MELD: Multi-Task Equilibrated Learning Detector for AI-Generated Text](https://mlsanity.com/paper/2605.06903/) (2026)
- [DetectZoo: A Unified Toolkit for AI-Generated Content Detection Across Text, Audio, and Image Modalities](https://mlsanity.com/paper/2606.04205/) (2026)
- [When New Generators Arrive: Lifelong Machine-Generated Text Attribution via Ridge Feature Transfer](https://mlsanity.com/paper/2606.05626/) (2026)
- [ARB: A Matched Authorship-Rewriting Benchmark Dataset for AI-Text Detector Evaluation](https://mlsanity.com/paper/2607.29539/) (2026)
- [On the Salience of Low-Probability Tokens for AI-Generated Text Detection: A Multiscale Uncertainty Perspective](https://mlsanity.com/paper/2606.02158/) (2026)
- [Detecting undisclosed LLM-generated content in parliamentary texts](https://mlsanity.com/paper/2606.14209/) (2026)
- [DWT-Fusion: A Signal-Based Framework for Training-Free LLM-Generated Text Detection](https://mlsanity.com/paper/2607.22026/) (2026)
- [C-HAT-Bench: Benchmarking Chinese AI-Text Detection Beyond Fully Generated Text](https://mlsanity.com/paper/2609.32770/) (2026)

## Abstract (arXiv)

Large language models (LLMs) present significant risks when used to generate non-factual content and spread disinformation at scale. Detecting such LLM-generated content is crucial, yet current detectors often struggle to generalize in open-world contexts. We introduce Learning2Rewrite, a novel framework for detecting AI-generated text with exceptional generalization to unseen domains. Our method leverages the insight that LLMs inherently modify AI-generated content less than human-written text when tasked with rewriting. By training LLMs to minimize alterations on AI-generated inputs, we amplify this disparity, yielding a more distinguishable and generalizable edit distance across diverse text distributions. Extensive experiments on data from 21 independent domains and four major LLMs (GPT-3.5, GPT-4, Gemini, and Llama-3) demonstrate that our detector outperforms state-of-the-art detection methods by up to 23.04% in AUROC for in-distribution tests, 37.26% for out-of-distribution tests, and 48.66% under adversarial attacks. Our unique training objective ensures better generalizability compared to directly training for classification, when leveraging the same amount of parameters. Our findings suggest that reinforcing LLMs' inherent rewriting tendencies offers a robust and scalable solution for detecting AI-generated text.