The Impact of Prompts on Zero-Shot Detection of AI-Generated Text
In recent years, there have been significant advancements in the development of Large Language Models (LLMs). While their practical applications are now widespread, their potential for misuse, such as generating fake news and committing plagiarism, has posed significant concerns. To address this issue, detectors have been developed to evaluate whether a given text is human-generated or AI-generated. Among others, zero-shot detectors stand out as effective approaches that do not require additional training data and are often likelihood-based. In chat-based applications, users commonly input prompts and utilize the AI-generated texts. However, zero-shot detectors typically analyze these texts in isolation, neglecting the impact of the original prompts. It is conceivable that this approach may lead to a discrepancy in likelihood assessments between the text generation phase and the detection phase. So far, there remains an unverified gap concerning how the presence or absence of prompts impacts detection accuracy for zero-shot detectors. In this paper, we introduce an evaluative framework to empirically analyze the impact of prompts on the detection accuracy of AI-generated text. We assess various zero-shot detectors using both white-box detection, which leverages the prompt, and black-box detection, which operates without prompt information. Our experiments reveal the significant influence of prompts on detection accuracy. Remarkably, compared with black-box detection without prompts, the white-box methods using prompts demonstrate an increase in AUC of at least $0.1$ across all zero-shot detectors tested. Code is available: \url{https://github.com/kaito25atugich/Detector}.
Code (1)
Tasks
Text GenerationSimilar Papers 제목 키워드 기반
Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-ranker
Re-rankers, which order retrieved documents with respect to the relevance score on the given query, have gained attention for the information retrieval (IR) task. Rather than fine-tuning the pre-trained language model (P…
Information RetrievalLanguage ModelingLanguage ModellingRe-Ranking+1AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection
Zero-shot anomaly detection (ZSAD) targets the identification of anomalies within images from arbitrary novel categories. This study introduces AdaCLIP for the ZSAD task, leveraging a pre-trained vision-language model (V…
Anomaly DetectionLanguage ModelingLanguage Modellingzero-shot anomaly detectionThe Art of Prompting: Event Detection based on Type Specific Prompts
We compare various forms of prompts to represent event types and develop a unified framework to incorporate the event type specific prompts for supervised, few-shot, and zero-shot event detection. The experimental result…
Event DetectionVocal Bursts Type PredictionThe Art of Prompting: Event Detection based on Type Specific Prompts
We compare various forms of prompts to represent event types and develop a unified framework to incorporate the event type specific prompts for supervised, few-shot, and zero-shot event detection. The experimental result…
Event DetectionVocal Bursts Type PredictionAutomatic Prompt Generation and Grounding Object Detection for Zero-Shot Image Anomaly Detection
Identifying defects and anomalies in industrial products is a critical quality control task. Traditional manual inspection methods are slow, subjective, and error-prone. In this work, we propose a novel zero-shot trainin…
Anomaly DetectionImage-text matchingLanguage ModelingLanguage Modelling+4