Chain of Hindsight aligns Language Models with Feedback.
Hao LiuCarmelo SferrazzaPieter AbbeelPublished in: ICLR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- document retrieval
- information retrieval
- speech recognition
- language modelling
- retrieval model
- test collection
- context sensitive
- query expansion
- statistical language models
- vector space model
- ad hoc information retrieval
- relevance feedback
- pseudo relevance feedback
- document length
- okapi bm
- language models for information retrieval
- query terms
- user feedback
- relevance model
- information extraction