Expert annotators who frequently use LLMs for writing detected AI-generated non-fiction articles with 99.3% accuracy by majority vote, outperforming all but one commercial detector.
We asked O1-P RO to first generate an article using the prompt tem- plate depicted in Table 8, then instructed the model to make it sound more human
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text
Expert annotators who frequently use LLMs for writing detected AI-generated non-fiction articles with 99.3% accuracy by majority vote, outperforming all but one commercial detector.