# Trace Is In Sentences: Unbiased Lightweight ChatGPT-Generated Text Detector

arXiv: https://arxiv.org/abs/2509.18535 · HTML: https://mlsanity.com/paper/2509.18535/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [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)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond](https://mlsanity.com/paper/2109.00725/) (2021)
- [GPT detectors are biased against non-native English writers](https://mlsanity.com/paper/2304.02819/) (2023)
- [Counterfactual Fairness in Text Classification through Robustness](https://mlsanity.com/paper/1809.10610/) (2018)
- [Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification](https://mlsanity.com/paper/2108.08728/) (2021)
- [Ghostbuster: Detecting Text Ghostwritten by Large Language Models](https://mlsanity.com/paper/2305.15047/) (2023)
- [Causal Attention for Unbiased Visual Recognition](https://mlsanity.com/paper/2108.08782/) (2021)
- [Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests](https://mlsanity.com/paper/2106.00545/) (2021)
- [Multiscale Positive-Unlabeled Detection of AI-Generated Texts](https://mlsanity.com/paper/2305.18149/) (2023)
- [A Simple yet Efficient Ensemble Approach for AI-generated Text Detection](https://mlsanity.com/paper/2311.03084/) (2023)
- [Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend](https://mlsanity.com/paper/2302.02568/) (2023)

## Abstract (arXiv)

The widespread adoption of ChatGPT has raised concerns about its misuse, highlighting the need for robust detection of AI-generated text. Current word-level detectors are vulnerable to paraphrasing or simple prompts (PSP), suffer from biases induced by ChatGPT's word-level patterns (CWP) and training data content, degrade on modified text, and often require large models or online LLM interaction. To tackle these issues, we introduce a novel task to detect both original and PSP-modified AI-generated texts, and propose a lightweight framework that classifies texts based on their internal structure, which remains invariant under word-level changes. Our approach encodes sentence embeddings from pre-trained language models and models their relationships via attention. We employ contrastive learning to mitigate embedding biases from autoregressive generation and incorporate a causal graph with counterfactual methods to isolate structural features from topic-related biases. Experiments on two curated datasets, including abstract comparisons and revised life FAQs, validate the effectiveness of our method.