Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models.
Xiang JiSanjeev KulkarniMengdi WangTengyang XiePublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- document retrieval
- retrieval model
- query expansion
- speech recognition
- information retrieval
- language modelling
- test collection
- ad hoc information retrieval
- language models for information retrieval
- statistical language models
- vector space model
- document ranking
- query terms
- context sensitive
- relevance model
- smoothing methods
- language model for information retrieval
- translation model
- term dependencies
- pseudo relevance feedback
- okapi bm
- text classification
- knn
- spoken term detection
- bayesian networks