Probing LLMs for hate speech detection: strengths and vulnerabilities.
Sarthak RoyAshish HarshavardhanAnimesh MukherjeePunyajoy SahaPublished in: EMNLP (Findings) (2023)
Keyphrases
- detection algorithm
- detection accuracy
- automatic detection
- false positives
- detection rate
- object detection
- noisy environments
- detection method
- speech recognition
- text recognition
- hidden markov models
- speech signal
- false alarms
- event detection
- recognition engine
- speech synthesis
- information security
- information retrieval
- anomaly detection
- object recognition
- pattern recognition
- genetic algorithm