Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization.
Junkang WuYuexiang XieZhengyi YangJiancan WuJiawei ChenJinyang GaoBolin DingXiang WangXiangnan HePublished in: CoRR (2024)
Keyphrases
- language model
- robust optimization
- language modeling
- n gram
- probabilistic model
- information retrieval
- stochastic programming
- document retrieval
- query expansion
- retrieval model
- speech recognition
- language modelling
- test collection
- statistical language models
- smoothing methods
- context sensitive
- language models for information retrieval
- ad hoc information retrieval
- decision trees
- document ranking
- relevance model
- pseudo relevance feedback
- vector space model
- document length
- spoken term detection