Active Preference Learning for Large Language Models.
William MuldrewPeter HayesMingtian ZhangDavid BarberPublished in: CoRR (2024)
Keyphrases
- language model
- preference learning
- language modeling
- ordinal regression
- probabilistic model
- gaussian processes
- document retrieval
- pairwise comparison
- n gram
- language modelling
- recommender systems
- information retrieval
- retrieval model
- statistical language models
- ranking functions
- test collection
- query expansion
- smoothing methods
- pairwise
- support vector
- gaussian process
- binary classification
- expectation maximization
- search engine