Aligning Modalities in Vision Large Language Models via Preference Fine-tuning.
Yiyang ZhouChenhang CuiRafael RafailovChelsea FinnHuaxiu YaoPublished in: CoRR (2024)
Keyphrases
- fine tuning
- language model
- language modeling
- n gram
- document retrieval
- probabilistic model
- information retrieval
- retrieval model
- viable alternative
- speech recognition
- computer vision
- language modelling
- statistical language models
- fine tune
- context sensitive
- smoothing methods
- query expansion
- user preferences
- ad hoc information retrieval
- fine tuned
- test collection
- machine learning
- word error rate
- query terms
- query specific
- passage retrieval
- vector space model
- term dependencies
- cross lingual
- multi modal
- domain specific
- text mining
- image understanding
- language models for information retrieval