Explaining Multi-modal Large Language Models by Analyzing their Vision Perception.
Loris GiuliviGiacomo BoracchiPublished in: CoRR (2024)
Keyphrases
- multi modal
- language model
- language modeling
- n gram
- document retrieval
- speech recognition
- probabilistic model
- information retrieval
- language modelling
- test collection
- query expansion
- computer vision
- audio visual
- retrieval model
- context sensitive
- smoothing methods
- statistical language models
- multi modality
- language models for information retrieval
- image annotation
- relevance model
- document ranking
- cross modal
- retrieval systems
- text classification
- high dimensional
- metadata
- uni modal
- spoken term detection