SatIR: Scalable High-Recall Constraint-Satisfaction-Based Information Retrieval for Clinical Trials Matching

arXiv:2604.08849 · cs.CL, cs.AI, cs.DB, cs.MA, cs.SC · Submitted 2026-04-10 · Read on arXiv

cs.CL, cs.AI, cs.DB, cs.MA, cs.SC

Submitted: 2026-04-10

Updated: 2026-09-14

Comments: Accepted at COLM 2026. 125 pages (11 pages main text, 110 pages appendix), 24 figures, 27 tables. Code: https://github.com/stanford-oval/clinical-trial-matching Project page: https://satir.genie.stanford.edu

Code: https://github.com/stanford-oval/clinical-trial-matching

Project page: https://satir.genie.stanford.edu

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Ontology — 80× in this paper · explained in 2 episodes
• Benchmark — 25× in this paper · explained in 2 episodes
• Grounding — 22× in this paper · explained in 3 episodes
• Ablation — 14× in this paper · explained in 1 episode
• Core — 13× in this paper · explained in 2 episodes
• Verification — 13× in this paper · explained in 2 episodes
• Verifier — 12× in this paper · explained in 2 episodes
• Consistency — 9× in this paper · explained in 3 episodes
• Accuracy — 8× in this paper · explained in 1 episode
• Fidelity — 6× in this paper · explained in 2 episodes
• Provenance — 6× in this paper · explained in 4 episodes
• Interpretability — 5× in this paper · explained in 15 episodes
• Trace — 5× in this paper · explained in 2 episodes
• Adam — 4× in this paper · explained in 2 episodes
• Formal Methods — 4× in this paper · explained in 3 episodes
• Satisfiability Modulo Theories — 4× in this paper
• Semantic Drift — 4× in this paper · explained in 3 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Entity Grounding — 3× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• LLM judge — 3× in this paper · explained in 2 episodes
• Pruning — 3× in this paper · explained in 4 episodes
• SMT solver — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Admissibility — 2× in this paper · explained in 2 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Axioms — 2× in this paper · explained in 2 episodes
• Expression Constraint Language — 2× in this paper
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Empirical Methods in Natural Language Processing — 1× in this paper
• Failure Modes — 1× in this paper · explained in 3 episodes
• Failure Taxonomy — 1× in this paper · explained in 2 episodes
• Modularity — 1× in this paper · explained in 9 episodes
• Personalization — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Structural Integrity — 1× in this paper · explained in 3 episodes

Sources

• De-conflating Preference and Qualification: Constrained Dual-Perspective Reasoning for Job Recommendation with Large Language Models
• LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers
• Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning
• Semantic Operators: A Declarative Model for Rich, AI-based Data Processing
• OpenAI GPT-5 System Card

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering