How You Prompt Matters! Even Task-Oriented Constraints in Instructions Affect LLM-Generated Text Detection

arXiv:2311.08369v2 Announce Type: replace
Abstract: To combat the misuse of Large Language Models (LLMs), many recent studies have presented LLM-generated-text detectors with promising performance. When users instruct LLMs to generate texts, the instruction can include different constraints depending on the user's need. However, most recent studies do not cover such diverse instruction patterns when creating datasets for LLM detection. In this paper, we find that even task-oriented constraints -- constraints that would naturally be included in an instruction and are …

abstract arxiv constraints cs.cl detection generate generated language language models large language large language models llm llms misuse performance prompt studies text type