# LLM Encoder vs. Decoder: Robust Detection of Chinese AI-Generated Text with LoRA

arXiv: https://arxiv.org/abs/2509.00731 · HTML: https://mlsanity.com/paper/2509.00731/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 31 Aug 2025.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [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)
- [All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text](https://mlsanity.com/paper/2107.00061/) (2021)
- [Revisiting Pre-Trained Models for Chinese Natural Language Processing](https://mlsanity.com/paper/2004.13922/) (2020)
- [Automatic Detection of Generated Text is Easiest when Humans are Fooled](https://mlsanity.com/paper/1911.00650/) (2019)
- [Automatic Detection of Machine Generated Text: A Critical Survey](https://mlsanity.com/paper/2011.01314/) (2020)
- [Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models](https://mlsanity.com/paper/2311.04378/) (2023)
- [Multiscale Positive-Unlabeled Detection of AI-Generated Texts](https://mlsanity.com/paper/2305.18149/) (2023)
- [LLM-Detector: Improving AI-Generated Chinese Text Detection with Open-Source LLM Instruction Tuning](https://mlsanity.com/paper/2402.01158/) (2024)
- [On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks](https://mlsanity.com/paper/2407.04794/) (2024)
- [Advanced Predictive Modeling for Enhanced Mortality Prediction in ICU Stroke Patients Using Clinical Data](https://mlsanity.com/paper/2407.14211/) (2024)

## Built on by (most cited first, 1 of 1)

- [Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models](https://mlsanity.com/paper/2606.03165/) (2026)

## Abstract (arXiv)

The rapid growth of large language models (LLMs) has heightened the demand for accurate detection of AI-generated text, particularly in languages like Chinese, where subtle linguistic nuances pose significant challenges to current methods. In this study, we conduct a systematic comparison of encoder-based Transformers (Chinese BERT-large and RoBERTa-wwm-ext-large), a decoder-only LLM (Alibaba's Qwen2.5-7B/DeepSeek-R1-Distill-Qwen-7B fine-tuned via Low-Rank Adaptation, LoRA), and a FastText baseline using the publicly available dataset from the NLPCC 2025 Chinese AI-Generated Text Detection Task. Encoder models were fine-tuned using a novel prompt-based masked language modeling approach, while Qwen2.5-7B was adapted for classification with an instruction-format input and a lightweight classification head trained via LoRA. Experiments reveal that although encoder models nearly memorize training data, they suffer significant performance degradation under distribution shifts (RoBERTa: 76.3% test accuracy; BERT: 79.3%). FastText demonstrates surprising lexical robustness (83.5% accuracy) yet lacks deeper semantic understanding. In contrast, the LoRA-adapted Qwen2.5-7B achieves 95.94% test accuracy with balanced precision-recall metrics, indicating superior generalization and resilience to dataset-specific artifacts. These findings underscore the efficacy of decoder-based LLMs with parameter-efficient fine-tuning for robust Chinese AI-generated text detection. Future work will explore next-generation Qwen3 models, distilled variants, and ensemble strategies to enhance cross-domain robustness further.