Visual Hallucinations of Multi-modal Large Language Models.
Wen HuangHongbin LiuMinxin GuoNeil GongPublished in: ACL (Findings) (2024)
Keyphrases
- multi modal
- language model
- cross modal
- language modeling
- n gram
- probabilistic model
- speech recognition
- document retrieval
- video search
- single modality
- language modelling
- retrieval model
- multi modality
- test collection
- query expansion
- information retrieval
- statistical language models
- smoothing methods
- multiple modalities
- language models for information retrieval
- auto annotation
- audio visual
- semantic concepts
- visual features
- translation model
- relevance model
- visual information
- document ranking
- image annotation
- uni modal
- low level
- multimedia