AI RESEARCH
ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability
arXiv CS.CL
•
ArXi:2502.11336v2 Announce Type: replace Detecting texts generated by Large Language Models (LLMs) could cause grave mistakes due to incorrect decisions, such as undermining students' academic dignity. LLM text detection thus needs to ensure the interpretability of the decision, which can help users judge how reliably correct its prediction is. When humans verify whether a text is human-written or LLM-generated, they intuitively investigate which of them it shares similar spans with.