The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models.
Yan LiuYu LiuXiaokang ChenPin-Yu ChenDaoguang ZanMin-Yen KanTsung-Yi HoPublished in: CoRR (2024)
Keyphrases
- language model
- pre trained
- language modeling
- n gram
- information retrieval
- retrieval model
- probabilistic model
- speech recognition
- neural network
- document retrieval
- training data
- training examples
- query expansion
- test collection
- language modelling
- statistical language models
- relevance model
- smoothing methods
- control signals
- decision trees
- language models for information retrieval
- data sets
- relevance feedback
- active learning
- multimedia
- computer vision
- learning algorithm