Performance of large language models in numerical vs. semantic medical knowledge: Benchmarking on evidence-based Q&As.
Eden AvnatMichal LevyDaniel HerstainElia YankoDaniel Ben JoyaMichal Tzuchman KatzDafna EshelSahar LarosYael DaganShahar BaramiJoseph MermelsteinShahar OvadiaNoam ShomronVarda ShalevRaja-Elie E. AbdulnourPublished in: CoRR (2024)
Keyphrases
- medical knowledge
- language model
- medical diagnosis
- language modeling
- clinical data
- semi automatic
- knowledge based systems
- document retrieval
- n gram
- clinical practice
- clinical guidelines
- probabilistic model
- speech recognition
- retrieval model
- query expansion
- information retrieval
- knowledge sources
- statistical language models
- language modelling
- language models for information retrieval
- document ranking
- test collection
- case base
- natural language
- pseudo relevance feedback
- relevance model
- medical images
- domain specific
- case based reasoning
- statistical language modeling
- query terms
- smoothing methods
- vector space model
- image processing