Aligner: One Global Token is Worth Millions of Parameters When Aligning Large Language Models.
Ziheng ZhouYingnian WuSong-Chun ZhuDemetri TerzopoulosPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- document retrieval
- probabilistic model
- n gram
- language modelling
- speech recognition
- test collection
- retrieval model
- context sensitive
- information retrieval
- mixture model
- statistical language models
- query expansion
- ad hoc information retrieval
- query terms
- relevance model
- vector space model
- maximum likelihood
- document ranking
- expectation maximization
- pseudo relevance feedback
- translation model
- smoothing methods
- language model for information retrieval