Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge.
Tianhao WuWeizhe YuanOlga GolovnevaJing XuYuandong TianJiantao JiaoJason WestonSainbayar SukhbaatarPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- language modelling
- n gram
- document retrieval
- information retrieval
- test collection
- speech recognition
- query expansion
- retrieval model
- vector space model
- smoothing methods
- translation model
- document length
- language model for information retrieval
- context sensitive
- hidden markov models
- tf idf
- passage retrieval
- document ranking
- machine learning
- statistical language models
- okapi bm