Papers with DetectGPT
GPT-who: An Information Density-based Machine-Generated Text Detector (2024.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) generate misinformation, memorized content, plagiarized content, toxic speech, and hallucinated content. |
| Approach: | They propose a statistical detector that uses UID to model the unique statistical signature of each LLM and human author for accurate detection. |
| Outcome: | The proposed method outperforms state-of-the-art detectors by over 20% across domains. |
Ghostbuster: Detecting Text Ghostwritten by Large Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Ghostbuster is a system that passes documents through weaker language models, runs a structured search over possible combinations of their features, and trains a classifier on the selected features. |
| Approach: | They propose a method that passes documents through weaker language models, runs a structured search over possible combinations of their features, and trains a classifier on the selected features. |
| Outcome: | The proposed method outperforms existing detectors and a new baseline on student essays, creative writing, and news articles. |
Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Better (2024.acl-long)
Copied to clipboard
Shengchao Liu, Xiaoming Liu, Yichen Wang, Zehua Cheng, Chengzhengxu Li, Zhaohan Zhang, Yu Lan, Chao Shen
| Challenge: | Existing methods to detect MGT from human-written texts are inadequate . existing methods are fine-tuned and zero-shot metric-based, but they can be more accurate. |
| Approach: | They propose a novel fine-tuned detector that can detect MGT from human-written texts by contrastive learning on selective perturbation. |
| Outcome: | The proposed method outperforms the state-of-the-art by 1.20% on four public datasets. |
Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models can be used to produce text that is coherent, well-written, and persuasive . some individuals have misused LLMs for nefarious purposes, such as creating fake news articles or engaging in cheating . |
| Approach: | They propose to incorporate a Bayesian surrogate model to improve query efficiency . they propose to select typical samples based on Bayes' uncertainty and interpolate scores . |
| Outcome: | The proposed method significantly outperforms existing approaches under a low query budget. |
Detecting Machine-Generated Long-Form Content with Latent-Space Variables (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing zero-shot methods to distinguish machine-generated long-form texts from humans are vulnerable to domain shift including different decoding strategies, variations in prompts, and attacks. |
| Approach: | They propose a method that incorporates abstract elements as key deciding factors by training a latent-space model on sequences of events or topics derived from human-written texts. |
| Outcome: | The proposed method improves on baselines on three domains and significantly improves over existing methods. |