The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language Models.
Yan LiuYu LiuXiaokang ChenPin-Yu ChenDaoguang ZanMin-Yen KanTsung-Yi HoPublished in: ICLR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- document retrieval
- n gram
- information retrieval
- speech recognition
- retrieval model
- query expansion
- test collection
- language modelling
- smoothing methods
- language models for information retrieval
- context sensitive
- document ranking
- ad hoc information retrieval
- language model for information retrieval
- statistical language models
- relevance model
- document length
- vector space model
- language modeling framework
- query terms
- translation model
- word error rate
- bayesian networks
- search engine