MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models.
Chaoyou FuPeixian ChenYunhang ShenYulei QinMengdan ZhangXu LinZhenyu QiuWei LinJinrui YangXiawu ZhengKe LiXing SunRongrong JiPublished in: CoRR (2023)
Keyphrases
- language model
- comprehensive evaluation
- language modeling
- n gram
- query expansion
- probabilistic model
- document retrieval
- systematic evaluation
- information retrieval
- language modelling
- multi modal
- speech recognition
- retrieval model
- context sensitive
- ad hoc information retrieval
- test collection
- smoothing methods
- query terms
- vector space model
- statistical language models
- pseudo relevance feedback
- translation model
- language models for information retrieval
- feature selection
- relevance model
- document length
- word error rate
- term dependencies
- document ranking
- okapi bm
- multimedia
- language model for information retrieval