Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models.
Shrimai PrabhumoyeMostofa PatwaryMohammad ShoeybiBryan CatanzaroPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- probabilistic model
- statistical language models
- language modelling
- information retrieval
- language model for information retrieval
- query terms
- retrieval model
- query expansion
- test collection
- document ranking
- context sensitive
- cross lingual
- vector space model
- relevance model
- query specific
- document collections
- ad hoc information retrieval