Published March 4, 2024 | Version v1
Dataset Restricted

Lying Blindly: Bypassing ChatGPT's Safeguards to Generate Hard-to-Detect Disinformation Claims (Dataset)

Authors/Creators

  • 1. ROR icon University of Sheffield

Files

Restricted

The record is publicly accessible, but files are restricted to users with access.

Additional details

Related works

Is described by
arXiv:2402.08467 (arXiv)

Software

Repository URL
https://github.com/GateNLP/chatgpt-ukraine-disinfo