MaxMin-RLHF: Towards Equitable Alignment of Large Language Models with Diverse Human Preferences.
Souradip ChakrabortyJiahao QiuHui YuanAlec KoppelFurong HuangDinesh ManochaAmrit Singh BediMengdi WangPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- document retrieval
- n gram
- probabilistic model
- speech recognition
- information retrieval
- query expansion
- retrieval model
- statistical language models
- context sensitive
- ad hoc information retrieval
- test collection
- language modelling
- language model for information retrieval
- query terms
- vector space model
- document ranking
- smoothing methods
- term dependencies
- user preferences
- pseudo relevance feedback
- translation model
- document level
- query specific
- word error rate
- co occurrence
- active learning