Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks.
Jack GallifantShan ChenPedro MoreiraNikolaj MunchMingye GaoJackson PondLeo Anthony CeliHugo J. W. L. AertsThomas HartvigsenDanielle S. BittermanPublished in: CoRR (2024)
Keyphrases
- language model
- entity extraction
- language modeling
- n gram
- information retrieval
- probabilistic model
- document retrieval
- query expansion
- retrieval model
- text mining
- information extraction
- test collection
- query terms
- speech recognition
- ad hoc information retrieval
- named entities
- vector space model
- language modelling
- translation model
- pseudo relevance feedback
- context sensitive
- statistical language models
- keywords
- language model for information retrieval
- search engine
- document ranking
- relevance model
- machine learning
- natural language
- co occurrence