ALaRM: Align Language Models via Hierarchical Rewards Modeling.
Yuhang LaiSiyuan WangShujun LiuXuanjing HuangZhongyu WeiPublished in: ACL (Findings) (2024)
Keyphrases
- language model
- language modeling
- document retrieval
- retrieval model
- n gram
- language modelling
- statistical language models
- query expansion
- speech recognition
- information retrieval
- probabilistic model
- statistical language modeling
- test collection
- language models for information retrieval
- language model for information retrieval
- ad hoc information retrieval
- smoothing methods
- relevance model
- word error rate
- document ranking