CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generation.
Rahul MadhavanRishabh GargKahini WadhawanSameep MehtaPublished in: ACL (Findings) (2023)
Keyphrases
- language model
- language modeling
- document retrieval
- n gram
- probabilistic model
- information retrieval
- document level
- statistical language models
- language modelling
- smoothing methods
- test collection
- speech recognition
- retrieval model
- query expansion
- query terms
- context sensitive
- vector space model
- language models for information retrieval
- word error rate
- language model for information retrieval
- document ranking
- pseudo relevance feedback
- document length
- query specific
- ad hoc information retrieval
- chinese characters