Reward modeling for mitigating toxicity in transformer-based language models.
Farshid FaalKetra A. SchmittJia Yuan YuPublished in: Appl. Intell. (2023)
Keyphrases
- language model
- language modeling
- probabilistic model
- document retrieval
- n gram
- retrieval model
- language modelling
- query expansion
- information retrieval
- statistical language models
- speech recognition
- statistical language modeling
- context sensitive
- smoothing methods
- vector space model
- translation model
- text classification
- document ranking
- language model for information retrieval
- ad hoc information retrieval
- word error rate
- test collection
- query terms
- term dependencies
- machine learning
- passage retrieval
- pseudo relevance feedback