mlsanityData to 14 Oct 2026

Unmentioned Checklist Findings Change How Reinforcement Learning Appears to Improve Chest Radiograph Report Checking

arXiv 2610.05425 ↗First posted 4 Oct 2026cs.CV cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Automated checks of radiology reports may rely on AI-generated checklists that leave findings unmentioned. We used reinforcement learning to train a vision-language model to fill in a 12-finding checklist from a chest radiograph without seeing the sentence under test; a separate checking model judged the sentence from the checklist. On held-out patients, a rule-based check and an independent medical checker, neither used in training, measured discrimination gains (Youden index) of 12.6% and 11.8%; only the rule-based check met the prespecified false-alarm criterion. Switching to the training format, which fixes finding order and enters unmentioned findings as absent, raised the training checker's measured gain and lowered the independent checker's, a prespecified comparison that yielded 6.2% (95% interval 2.0% to 10.5%) and, post hoc on held-out patients, 7.7%. Across 8 checking models, acceptance of a label-consistent negative statement about an unmentioned finding ranged from 1.0% to 97.0%. Labels were report-derived, not radiologist-adjudicated.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 49 of its 61 references that are in the map. First posted on arXiv 4 Oct 2026.

Builds on

49 of 61 references.

References · 49

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  6. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  7. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  8. 2025Qwen2.5-VL Technical Reportcited by 5,587
  9. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  10. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,516
  11. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  12. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,729
37 more
  1. 2016Concrete Problems in AI Safetycited by 1,642
  2. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,423
  3. 2022Scaling Laws for Reward Model Overoptimizationcited by 1,095
  4. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Trainingcited by 1,053
  5. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?cited by 914
  6. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 817
  7. 2024Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMscited by 735
  8. 2018Object Hallucination in Image Captioningcited by 669
  9. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Modelscited by 665
  10. 2025VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Modelcited by 526
  11. 2025Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAscited by 521
  12. 2025Visual-RFT: Visual Reinforcement Fine-Tuningcited by 513
  13. 2024MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmarkcited by 372
  14. 2017Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answeringcited by 339
  15. 2020CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERTcited by 337
  16. 2021RadGraph: Extracting Clinical Entities and Relations from Radiology Reportscited by 319
  17. 2025MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learningcited by 173
  18. 2024GREEN: Generative Radiology Report Evaluation and Error Notationcited by 128
  19. 2024CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formatscited by 106
  20. 2025Self-Rewarding Vision-Language Model via Reasoning Decompositioncited by 97
  21. 2025CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learningcited by 38
  22. 2024ReXTrust: A Model for Fine-Grained Hallucination Detection in AI-Generated Radiology Reportscited by 12
  23. 2026CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioningcited by 8
  24. 2026Judge Reliability Harness: Stress Testing the Reliability of LLM Judgescited by 8
  25. 2026CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioningcited by 8
  26. 2023Fact-Checking of AI-Generated Reportscited by 7
  27. 2026Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoningcited by 7
  28. 2026MM-JudgeBias: A Benchmark for Evaluating Compositional Biases in MLLM-as-a-Judgecited by 4
  29. 2026A Judge Should Know What Changed:Construct Validity for LLM-as-a-Judge Evaluationcited by 4
  30. 2026MJ1: Multimodal Judgment via Grounded Verificationcited by 3
  31. 2026Verification Mirage: Mapping the Reliability Boundary of Self-Verification in Medical VQAcited by 2
  32. 2026Do Image-Text Metrics Respect Semantic Invariances?cited by 2
  33. 2026Commit-first LLM judging inherits the judge's own errorscited by 2
  34. 2025Process Reward Models for Sentence-Level Verification of LVLM Radiology Reportscited by 1
  35. 2026See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RLcited by 1
  36. 2026Catching Hallucinated Citations in Video-LLM Question Answering: A Self-Verification Pipeline and Verifier Ablation Studycited by 1
  37. 2026ModaLens: Measuring Image Sensitivity in Report-Conditioned Medical VLMscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Enhancing Visual Reasoning in Chest X-Ray Report Generation Using Reinforcement Learning
  2. 2025RadHiera: Semantic Hierarchical Reinforcement Learning for Medical Report Generation
  3. 2025Reason Like a Radiologist: Chain-of-Thought and Reinforcement Learning for Verifiable Report Generation
  4. 2026Rethinking the Efficiency and Effectiveness of Reinforcement Learning for Radiology Report Generation
  5. 2025Enhancing Radiology Report Generation and Visual Grounding using Reinforcement Learning
  6. 2026Scaling medical imaging report generation with multimodal reinforcement learning
  7. 2026SDR: Set-Distance Rewards for Radiology Report Generation
  8. 2023Longitudinal Data and a Semantic Similarity Reward for Chest X-Ray Report Generation