Probing LLMs for hate speech detection: strengths and vulnerabilities.
Sarthak RoyAshish HarshavardhanAnimesh MukherjeePunyajoy SahaPublished in: CoRR (2023)
Keyphrases
- detection algorithm
- speech recognition
- automatic detection
- detection accuracy
- speech signal
- detection method
- detection rate
- speech synthesis
- false alarms
- object detection
- false positives
- audio visual
- information security
- probabilistic model
- pattern recognition
- countermeasures
- automatic speech recognition
- noisy environments
- speaker recognition
- video sequences