Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration.
Sunhao DaiWeihao LiuYuqi ZhouLiang PangRongju RuanGang WangZhenhua DongJun XuJi-Rong WenPublished in: ACL (Findings) (2024)
Keyphrases
- information retrieval
- document collections
- relevant documents
- information retrieval systems
- document retrieval
- vector space model
- test collection
- learning to rank
- real world
- retrieval systems
- maximal marginal relevance
- document indexing
- query expansion
- structured documents
- latent semantic indexing
- linguistic analysis
- language model
- distributed information retrieval
- relevance ranking
- term weighting
- search engine
- retrieved documents
- xml documents
- text documents
- text mining
- information access
- question answering
- automatic categorization
- text categorization
- related documents
- retrieval strategies
- retrieval model
- retrieval effectiveness
- information extraction
- automatically generated
- document classification
- language modeling
- text retrieval
- ad hoc retrieval
- effective retrieval
- trec collections
- latent semantic analysis
- patent documents
- keywords
- information retrieval evaluation
- document corpus