RRHF: Rank Responses to Align Language Models with Human Feedback without tears.
Zheng YuanHongyi YuanChuanqi TanWei WangSongfang HuangFei HuangPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- speech recognition
- information retrieval
- query expansion
- probabilistic model
- language modelling
- statistical language models
- retrieval model
- test collection
- context sensitive
- smoothing methods
- vector space model
- ad hoc information retrieval
- relevance model
- document ranking
- pseudo relevance feedback
- word error rate
- language models for information retrieval
- language model for information retrieval
- user feedback
- document length
- text retrieval
- okapi bm
- relevant documents
- spoken term detection