SatIR uses SMT solvers and LLMs to formalize clinical constraints and achieves 32-72% more relevant trial matches per patient than TrialGPT on a set of 59 patients and 3,621 trials.
It is very simple
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Scalable High-Recall Constraint-Satisfaction-Based Information Retrieval for Clinical Trials Matching
SatIR uses SMT solvers and LLMs to formalize clinical constraints and achieves 32-72% more relevant trial matches per patient than TrialGPT on a set of 59 patients and 3,621 trials.