CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Low Resource With Contrastive Learning

Xiaoming Liu, Zhaohan Zhang, Yichen Wang, Hang Pu, Yu Lan, Chao Shen


Abstract
Machine-Generated Text (MGT) detection, a task that discriminates MGT from Human-Written Text (HWT), plays a crucial role in preventing misuse of text generative models, which excel in mimicking human writing style recently. Latest proposed detectors usually take coarse text sequences as input and fine-tune pretrained models with standard cross-entropy loss. However, these methods fail to consider the linguistic structure of texts. Moreover, they lack the ability to handle the low-resource problem which could often happen in practice considering the enormous amount of textual data online. In this paper, we present a coherence-based contrastive learning model named CoCo to detect the possible MGT under low-resource scenario. To exploit the linguistic feature, we encode coherence information in form of graph into text representation. To tackle the challenges of low data resource, we employ a contrastive learning framework and propose an improved contrastive loss for preventing performance degradation brought by simple samples. The experiment results on two public datasets and two self-constructed datasets prove our approach outperforms the state-of-art methods significantly. Also, we surprisingly find that MGTs originated from up-to-date language models could be easier to detect than these from previous models, in our experiments. And we propose some preliminary explanations for this counter-intuitive phenomena. All the codes and datasets are open-sourced.
Anthology ID:
2023.emnlp-main.1005
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16167–16188
Language:
URL:
https://aclanthology.org/2023.emnlp-main.1005
DOI:
10.18653/v1/2023.emnlp-main.1005
Bibkey:
Cite (ACL):
Xiaoming Liu, Zhaohan Zhang, Yichen Wang, Hang Pu, Yu Lan, and Chao Shen. 2023. CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Low Resource With Contrastive Learning. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 16167–16188, Singapore. Association for Computational Linguistics.
Cite (Informal):
CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Low Resource With Contrastive Learning (Liu et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.1005.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.1005.mp4