mlsanityData to 14 Oct 2026

Answering clinicians' questions over trial evidence tables with verifiable, feedback-driven language models

arXiv 2610.02576 ↗First posted 1 Oct 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Systematic reviews condense clinical trials into evidence tables, yet clinicians can interrogate these tables only through database queries, and many questions concern attributes that the table does not record, such as a drug's target class or a harmonised endpoint. Here we introduce FD-SCoPE, a language-model framework that answers both kinds of question, exposes the query, the selected trials and the derivation rule behind every answer, and learns from expert corrections. On an oncology evidence table of 159 immune checkpoint inhibitor trial records, FD-SCoPE completed all 140 clinician-style tasks (alternatives, 90.7-97.9%). For questions needing derived attributes it retrieved 99.3% of relevant trial records at a positive predictive value of 89.8% and outperformed four alternative approaches (derived-value F1 77.7% versus 64.8-73.4%). Corrections on 299 questions, simulated from reference answers, raised F1 on 1,201 unseen questions from 77.9% to 84.9%. Language models coupled with executable queries, verified programs and expert feedback can give clinicians auditable access to trial evidence.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 46 references that are in the map. First posted on arXiv 1 Oct 2026.

Builds on

29 of 46 references.

References · 29

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  6. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  7. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  8. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  9. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  10. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 832
  11. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  12. 2022PAL: Program-aided Language Modelscited by 652
17 more
  1. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  2. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 411
  3. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  4. 2022Binding Language Models in Symbolic Languagescited by 228
  5. 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 164
  6. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 164
  7. 2024EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Recordscited by 78
  8. 2019Text-to-SQL Generation for Question Answering on Electronic Medical Recordscited by 77
  9. 2023Matching Patients to Clinical Trials with Large Language Modelscited by 69
  10. 2024A Framework for Human Evaluation of Large Language Models in Healthcare Derived from Literature Reviewcited by 66
  11. 2023Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustnesscited by 53
  12. 2023EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Recordscited by 45
  13. 2024BlendSQL: A Scalable Dialect for Unifying Hybrid Question Answering in Relational Algebracited by 24
  14. 2024TrustSQL: Benchmarking Text-to-SQL Reliability with Penalty-Based Scoringcited by 17
  15. 2024Accelerating Clinical Evidence Synthesis with Large Language Modelscited by 16
  16. 2026FD-NL2SQL: Feedback-Driven Clinical NL2SQL that Improves with Usecited by 2
  17. 2026SCOPE:Planning for Hybrid Querying over Clinical Trial Datacited by 1

Built on by

Not cited yet.