# Explaining Generalization of AI-Generated Text Detectors Through Linguistic Analysis

arXiv: https://arxiv.org/abs/2601.07974 · HTML: https://mlsanity.com/paper/2601.07974/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 51 references that are in the map.
- First posted on arXiv 12 Jan 2026.

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2401.12070/) (2024)
- [ASQA: Factoid Questions Meet Long-Form Answers](https://mlsanity.com/paper/2204.06092/) (2022)
- [Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders](https://mlsanity.com/paper/2403.03952/) (2024)
- [RADAR: Robust AI-Text Detection via Adversarial Learning](https://mlsanity.com/paper/2307.03838/) (2023)
- [RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors](https://mlsanity.com/paper/2405.07940/) (2024)
- [MAGE: Machine-generated Text Detection in the Wild](https://mlsanity.com/paper/2305.13242/) (2023)
- [On the Use of ArXiv as a Dataset](https://mlsanity.com/paper/1905.00075/) (2019)
- [Ghostbuster: Detecting Text Ghostwritten by Large Language Models](https://mlsanity.com/paper/2305.15047/) (2023)
- [Contrasting Linguistic Patterns in Human and LLM-Generated News Text](https://mlsanity.com/paper/2308.09067/) (2023)
- [DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning](https://mlsanity.com/paper/2410.20964/) (2024)
- [CHEAT: A Large-scale Dataset for Detecting ChatGPT-writtEn AbsTracts](https://mlsanity.com/paper/2304.12008/) (2023)
- [On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing](https://mlsanity.com/paper/2306.05524/) (2023)
- [StyloAI: Distinguishing AI-Generated Content with Stylometric Analysis](https://mlsanity.com/paper/2405.10129/) (2024)
- [StyloMetrix: An Open-Source Multilingual Tool for Representing Stylometric Vectors](https://mlsanity.com/paper/2309.12810/) (2023)
- [EAGLE: A Domain Generalization Framework for AI-generated Text Detection](https://mlsanity.com/paper/2403.15690/) (2024)
- [On the Generalization of Training-based ChatGPT Detection Methods](https://mlsanity.com/paper/2310.01307/) (2023)
- [Differentiating Between Human-Written and AI-Generated Texts Using Automatically Extracted Linguistic Features](https://mlsanity.com/paper/2407.03646/) (2024)

## Abstract (arXiv)

AI-text detectors achieve high accuracy on in-domain benchmarks, but often struggle to generalize across different generation conditions such as unseen prompts, model families, or domains. While prior work has reported these generalization gaps, there are limited insights about the underlying causes. In this work, we present a systematic study aimed at explaining generalization behavior through linguistic analysis. We construct a comprehensive benchmark that spans 6 prompting strategies, 7 large language models (LLMs), and 4 domain datasets, resulting in a diverse set of human- and AI-generated texts. Using this dataset, we fine-tune classification-based detectors on various generation settings and evaluate their cross-prompt, cross-model, and cross-dataset generalization. To explain the performance variance, we compute correlations between generalization accuracies and feature shifts of 80 linguistic features between training and test conditions. Our analysis reveals that generalization performance for specific detectors and evaluation conditions is significantly associated with linguistic features such as tense usage and pronoun frequency.