ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Capability for Large Vision-Language Models.
Shuo LiuKaining YingHao ZhangYue YangYuqi LinTianle ZhangChuanhao LiYu QiaoPing LuoWenqi ShaoKaipeng ZhangPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- speech recognition
- n gram
- query expansion
- statistical language models
- document retrieval
- retrieval model
- information retrieval
- language modelling
- probabilistic model
- test collection
- context sensitive
- smoothing methods
- relevance model
- pseudo relevance feedback
- passage retrieval
- translation model
- ad hoc information retrieval
- quantitative evaluation
- vector space model
- natural language
- bayesian networks
- language model for information retrieval
- machine learning
- query terms
- document ranking
- text mining
- language models for information retrieval