Accountable AI with Grounded, Faithful, Consistent, Actionable Rationales: A Case Study in Clinical Trial Matching with VERDICT

arXiv:2609.03366 · cs.CL, cs.CY, cs.LO · Submitted 2026-09-03 · Read on arXiv

cs.CL, cs.CY, cs.LO

Submitted: 2026-09-03

Updated: 2026-09-03

Comments: Accepted to EMNLP 2026 (Main Conference). 46 pages, 6 figures, 28 tables. Code and prompts: https://github.com/stanford-oval/clinical-trial-matching

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

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

Terminology

• Benchmark — 40× in this paper · explained in 2 episodes
• Accuracy — 31× in this paper · explained in 1 episode
• Accountability — 23× in this paper · explained in 2 episodes
• Aggregation — 23× in this paper · explained in 1 episode
• Trace — 20× in this paper · explained in 2 episodes
• Actionability — 15× in this paper · explained in 3 episodes
• SMT solver — 14× in this paper · explained in 2 episodes
• Consistency — 10× in this paper · explained in 3 episodes
• Arbiter — 9× in this paper · explained in 1 episode
• Adam — 7× in this paper · explained in 2 episodes
• Grounding — 7× in this paper · explained in 3 episodes
• Core — 3× in this paper · explained in 2 episodes
• Distillation — 3× in this paper · explained in 2 episodes
• LLM judge — 3× in this paper · explained in 2 episodes
• Satisfiability Modulo Theories — 3× in this paper
• Interpretability — 2× in this paper · explained in 15 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Decision-Support Tool — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Formal Methods — 1× in this paper · explained in 3 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Temporal Reasoning — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• GPT-4 Technical Report
• GPT-4o System Card
• Measuring Faithfulness in Chain-of-Thought Reasoning
• LLM Evaluators Recognize and Favor Their Own Generations
• Qwen2.5 Technical Report
• 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