Constraint-satisfaction retrieval with SMT, ontology grounding, and LLMs recovers 32–72% more eligible trials per patient than TrialGPT-style embedding retrieval on SIGIR 2016 and 1.8–3.2× higher eligible recall on a TREC 2022 subset.
patients with malignancies in remission are eligible
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SatIR: Scalable High-Recall Constraint-Satisfaction-Based Information Retrieval for Clinical Trials Matching
Constraint-satisfaction retrieval with SMT, ontology grounding, and LLMs recovers 32–72% more eligible trials per patient than TrialGPT-style embedding retrieval on SIGIR 2016 and 1.8–3.2× higher eligible recall on a TREC 2022 subset.