Vibe-Eval: A hard evaluation suite for measuring progress of multimodal language models.
Piotr PadlewskiMax BainMatthew HendersonZhongkai ZhuNishant RelanHai PhamDonovan OngKaloyan AleksievAitor OrmazabalSamuel PhuaEthan YeoEugenie LamprechtQi LiuYuqi WangEric ChenDeyu FuLei LiChe ZhengCyprien de Masson d'AutumeDani YogatamaMikel ArtetxeYi TayPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- speech recognition
- statistical language models
- language modelling
- probabilistic model
- document retrieval
- retrieval model
- query expansion
- information retrieval
- test collection
- context sensitive
- multi modal
- relevance model
- vector space model
- ad hoc information retrieval
- language models for information retrieval
- translation model
- document ranking
- smoothing methods
- query terms
- search engine
- pseudo relevance feedback
- evaluation metrics
- bayesian networks
- multimedia
- statistical language modeling