Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models.
Hannah Rose KirkYennie JunFilippo VolpinHaider IqbalElias BenussiFrédéric A. DreyerAleksandar ShtedritskiYuki M. AsanoPublished in: NeurIPS (2021)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- generative model
- speech recognition
- information retrieval
- document retrieval
- language modelling
- language modeling framework
- test collection
- query expansion
- statistical language models
- smoothing methods
- language models for information retrieval
- word error rate
- document ranking
- translation model
- relevance model
- pseudo relevance feedback
- vector space model
- retrieval model
- ad hoc information retrieval
- term dependencies
- context sensitive
- information retrieval systems
- term weighting
- query specific
- document length
- query terms
- text documents