Vanishing Gradients in Reinforcement Finetuning of Language Models.
Noam RazinHattie ZhouOmid SaremiVimal ThilakArwen BradleyPreetum NakkiranJoshua M. SusskindEtai LittwinPublished in: ICLR (2024)
Keyphrases
- language model
- language modeling
- n gram
- information retrieval
- document retrieval
- speech recognition
- probabilistic model
- query expansion
- retrieval model
- smoothing methods
- statistical language models
- language modelling
- ad hoc information retrieval
- test collection
- query terms
- context sensitive
- pseudo relevance feedback
- vector space model
- document ranking
- language models for information retrieval
- word error rate
- relevance model
- document length
- text retrieval
- word segmentation
- text classification
- information retrieval systems
- hidden markov models
- search engine