Multilingual large language models leak human stereotypes across language boundaries.
Yang Trista CaoAnna SotnikovaJieyu ZhaoLinda X. ZouRachel RudingerHal Daumé IIIPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- document retrieval
- comparable corpora
- cross lingual
- query expansion
- language modelling
- statistical language models
- information retrieval
- retrieval model
- language independent
- speech recognition
- test collection
- document ranking
- relevance model
- smoothing methods
- parallel corpus
- cross language
- vector space model
- context sensitive
- translation model
- ad hoc information retrieval
- pseudo relevance feedback
- text retrieval
- bilingual dictionaries
- language models for information retrieval
- language model for information retrieval
- term dependencies
- digital libraries
- natural language
- query specific
- cross language information retrieval
- web search
- information extraction
- statistical language modeling