'Quis custodiet ipsos custodes?' Who will watch the watchmen? On Detecting AI-generated peer-reviews
The integrity of the peer-review process is vital for maintaining scientific rigor and trust within the academic community. With the steady increase in the usage of large language models (LLMs) like ChatGPT in academic writing, there is a growing concern that AI-generated texts could compromise scientific publishing, including peer-reviews. Previous works have focused on generic AI-generated text detection or have presented an approach for estimating the fraction of peer-reviews that can be AI-generated. Our focus here is to solve a real-world problem by assisting the editor or chair in determining whether a review is written by ChatGPT or not. To address this, we introduce the Term Frequency (TF) model, which posits that AI often repeats tokens, and the Review Regeneration (RR) model, which is based on the idea that ChatGPT generates similar outputs upon re-prompting. We stress test these detectors against token attack and paraphrasing. Finally, we propose an effective defensive strategy to reduce the effect of paraphrasing on our models. Our findings suggest both our proposed methods perform better than the other AI text detectors. Our RR model is more robust, although our TF model performs better than the RR model without any attacks. We make our code, dataset, and model public.
Code (1)
Tasks
Text DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Real-Time Multimodal Data Collection Using Smartwatches and Its Visualization in Education
Wearable sensors, such as smartwatches, have become increasingly prevalent across domains like healthcare, sports, and education, enabling continuous monitoring of physiological and behavioral data. In the context of edu…
Autoencoder Watchdog Outlier Detection for Classifiers
Neural networks have often been described as black boxes. A generic neural network trained to differentiate between kittens and puppies will classify a picture of a kumquat as a kitten or a puppy. An autoencoder watch do…
Outlier DetectionregressionSequential Modeling with Multiple Attributes for Watchlist Recommendation in E-Commerce
In e-commerce, the watchlist enables users to track items over time and has emerged as a primary feature, playing an important role in users' shopping journey. Watchlist items typically have multiple attributes whose val…
AttributeSequential RecommendationSnowWatch: Snow Monitoring through Acquisition and Analysis of User-Generated Content
We present a system for complementing snow phenomena monitoring with virtual measurements extracted from public visual content. The proposed system integrates an automatic acquisition and analysis of photographs and webc…
Yes, Prime Minister, question order does matter -- and it's certainly not classical! But is it quantum?
Response to a poll can be manipulated by means of a series of leading questions. We show that such phenomena cannot be explained by use of classical probability theory, whereas quantum probability theory admits a possibi…