M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection.
Yuxia WangJonibek MansurovPetar IvanovJinyan SuArtem ShelmanovAkim TsvigunChenxi WhitehouseOsama Mohammed AfzalTarek MahmoudToru SasakiThomas ArnoldAlham Fikri AjiNizar HabashIryna GurevychPreslav NakovPublished in: EACL (1) (2024)
Keyphrases
- black box
- multi domain
- multi lingual
- text detection
- information access
- language independent
- domain specific
- cross domain
- information retrieval
- cross lingual
- object recognition
- connected components
- video analysis
- test cases
- digital libraries
- feature selection
- user behavior
- test collection
- video database
- heterogeneous networks
- text lines
- web documents
- active learning