Don't Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detection.
Min ZhangJianfeng HeTaoran JiChang-Tien LuPublished in: ACL (1) (2024)
Keyphrases
- false alarm rate
- object detection
- speech recognition
- automatic detection
- detection rate
- detection method
- false positives
- false alarms
- camera calibration
- high sensitivity
- detection algorithm
- detection accuracy
- high resolution
- speech signal
- audio visual
- stereo camera
- automatic speech recognition
- anomaly detection
- broadcast news
- neural network
- text recognition
- endpoint detection
- voice activity detection