MedAD-R1: Consistency-Reinforced Policy Optimization for Interpretable Medical Anomaly Detection

Haitao Zhang; Yingying Wang; Jiaxiang Wang; Haote Xu; Hongyang Zhang; Yirong Chen; Yue Huang; Xinghao Ding

cs.CVFeb 1, 2026

MedAD-R1: Consistency-Reinforced Policy Optimization for Interpretable Medical Anomaly Detection

Authors: Haitao Zhang, Yingying Wang, Jiaxiang Wang, Haote Xu, Hongyang Zhang, Yirong Chen, Yue Huang, Xinghao Ding

Organizations: School of Informatics, Xiamen University · Institute of Artificial Intelligence, Xiamen University · Zhejiang Expressway Co., Ltd. · School of Transportation Sclence and Engineering, Beihang University · School of Science and Engineering, Chinese University of Hong Kong · Shanghai Artificial Intelligence Laboratory

Abstract

Medical Anomaly Detection (MedAD) offers a promising direction for medical image analysis with Large Multimodal Models (LMMs). However, progress is limited by fragmented datasets and the tendency of Supervised Fine-Tuning (SFT) to learn superficial image-text correlations rather than verifiable diagnostic reasoning. Consequently, current models often generate fluent explanations that are either insufficiently grounded in the image or inconsistent with their final answers, limiting their reliability in high-stakes medical applications. To address these issues, we introduce MedAD-38K, a large-scale, multimodal, and multicenter benchmark containing structured Visual Question Answering pairs and quality-controlled diagnostic Chain-of-Thought annotations across five core MedAD tasks. Based on this benchmark, we propose a two-stage framework. Cognitive Injection first uses SFT to inject domain-specific medical knowledge and establish a structured think-then-answer format. Consistency Group Relative Policy Optimization (Con-GRPO) then employs an Evidence-Aware Consistency Reward to reinforce reasoning that remains grounded in the image and logically supports the final answer. The resulting MedAD-R1 achieves state-of-the-art performance on MedAD-38K and consistently outperforms all evaluated baselines across five source-disjoint external datasets spanning diverse imaging modalities. Beyond accuracy, it achieves higher reasoning-answer consistency and visual-grounding scores across multiple backbones. With only 0.8B parameters, MedAD-R1 offers practical potential for resource-constrained deployment. These results demonstrate the generality of evidence-aware consistency optimization for interpretable MedAD. Project resources are available at https://github.com/zhtstar/MedAD-R1.

Figures & tables

Figure 1: Comparison of traditional MedAD methods, general-purpose LMMs, and MedAD-R1. General LMMs may hallucinate findings (top) or produce reasoning inconsistent with the final answer (bottom), whereas MedAD-R1 remains visually grounded and answer-consistent.

Figure 2: Examples of the five MedAD VQA tasks in MedAD-38K. Questions are formulated as multiple-choice problems to support standardized evaluation.

Figure 3: Overview of the MedAD-38K construction and MedAD-R1 training pipeline. Top panel: source labels, masks, and metadata determine the VQA answers. MedGemma-27B generates auxiliary image descriptions, Gemini 2.5 Pro drafts the CoT annotations, and human reviewers verify their quality. Bottom panel: Cognitive Injection first adapts the model through SFT, followed by Con-GRPO with an Evidence-Aware Consistency Reward scored by MedGemma-4B along five dimensions: visual grounding (VG), task relevance (TR), answer support (AS), no-hallucination (NH), and no-contradiction (NC).

Figure 4: The equal-area five-region spatial grid used to derive lesion-localization labels in MedAD-38K.

Model	Params	Anat.	Anom.	Loc.	Mod.	Path.	Overall	Consist.	EOverall	EConsist.
Qwen3.5-0.8B	0.8B	94.22	57.88	33.74	93.45	14.93	76.43	92.12	68.12	88.75
InternVL3.5-1B	1B	95.04	50.09	33.53	89.27	15.52	73.10	93.53	69.81	91.53
Qwen3VL-2B	2B	91.20	55.54	37.08	92.57	10.75	74.91	94.84	67.35	94.41
Qwen2.5VL-3B	3B	78.56	50.29	30.63	78.97	11.04	64.90	93.25	51.07	92.01
MiMo-VL-7B	7B	61.71	55.20	30.04	63.71	28.81	56.86	94.57	39.49	93.78
Qwen2.5VL-7B	7B	75.43	56.10	26.90	82.28	15.52	66.30	94.17	50.12	91.84

Table 1: Comparison on MedAD-38K and the external zero-shot test set. Anat.: anatomy identification; Anom.: anomaly detection; Loc.: lesion localization; Mod.: modality classification; Path.: pathology characterization. Overall and Consist. denote accuracy and reasoning–answer consistency on MedAD-38K; EOverall and EConsist. denote the corresponding external-set metrics. Overall values are micro-averaged over applicable VQA instances. ∗ marks medical LMMs and † marks larger models fine-tuned on our training data. Boldface denotes the best result and underlining the second best. Means and standard deviations over five inference passes are reported in supplementary Tables C.1 and C.4 .

Backbone	Setting	Overall $\uparrow$	Consist. $\uparrow$	EOverall $\uparrow$
Qwen3.5-0.8B	Zero-shot	76.43	92.12	68.12
	SFT only	90.89	94.35	88.36
	Con-GRPO	95.12	97.26	90.09
InternVL3.5-1B	Zero-shot	73.10	93.53	69.81
	SFT only	86.40	93.75	81.63
	Con-GRPO	92.31	96.73	83.72

Table 2: Cross-backbone effectiveness and ablation. For each backbone we report zero-shot, SFT-only, and full Con-GRPO. Overall and Consist. are measured on MedAD-38K; EOverall is measured on the external set. All metrics are reported as percentages, and higher is better (

\uparrow

Configuration	Overall $\uparrow$	Consist. $\uparrow$
RL-only (no SFT)	81.84 $\pm$ 2.41	88.90
SFT only	90.89 $\pm$ 0.27	94.35
SFT + Acc	92.76 $\pm$ 0.44	93.71
SFT + Acc + EAC (Ours)	95.12 $\pm$ 0.04	97.26

Table 3: Ablation of the training stages and reward terms on MedAD-38K. Acc: accuracy reward only. EAC: Evidence-Aware Consistency Reward. All values are percentages; higher is better.

Configuration	$\lambda_{\text{fmt}}$	$\lambda_{\text{acc}}$	$\lambda_{\text{eac}}$	Overall $\uparrow$
Format-focused	0.8	0.1	0.1	89.34
Accuracy-focused	0.1	0.8	0.1	93.12
Consistency-focused	0.1	0.1	0.8	93.88
Balanced (Ours)	1/3	1/3	1/3	95.12

Table 4: Ablation of Con-GRPO reward weights on MedAD-38K.

\lambda_{\text{eac}}

weights the Evidence-Aware Consistency Reward.

Appendix figures & tables24 assets

Supplementary material from the paper’s appendix.

Appendix

Source	Modality	Anatomy	Normal	Abnormal	Images	VQA Instances
ATLAS	CE-MRI	Liver	2,571	2,173	4,744	16,405
BACH	Microscopy	Breast	100	300	400	1,500
BUSI	Ultrasound	Breast	133	647	780	2,987
Br35H	MRI	Brain	1,500	801	2,301	7,704
BraTS2021	MRI	Brain	8,179	3,109	11,288	36,973
CVC-ClinicDB	Endoscopy	Gastrointestinal	0	612	612	2,448

Appendix

Table A.1: Source-level composition of MedAD-38K. VQA counts differ across sources because lesion localization and pathology characterization are generated only when the required source annotations are available.

Table 10

Table 11

Task	Source of Correct Answer	Candidate Pool	Applicability
Modality Classification	Source modality metadata	10 modalities	All images
Anatomy Identification	Source anatomy metadata	10 anatomical regions	All images
Anomaly Detection	Source normality label	Yes / No	All images
Lesion Localization	Source segmentation mask	Five spatial regions	Abnormal images with masks
Pathology Characterization	Source disease label	Predefined pathology set	Images with disease labels

Appendix

Table A.6: Mapping from source annotations to the five VQA tasks.

Figure A.1: Overall token-count distribution of the generated CoT annotations. The histogram (left) marks the mean and median with dashed lines, while the violin and box plots (right) show the density, quartiles, and long-tail outliers. Token counts use the Qwen3.5 tokenizer and include only the text inside the <think>...</think> tags, excluding all tags and final answers. Across the complete training set ( $N=78{,}121$ ), the mean is 68.1 tokens, the median is 67.0, the standard deviation is 10.9, and the observed range is 36–266 tokens.

Figure A.2: Token-count distributions of the CoT annotations for the five MedAD tasks. Boxes represent the interquartile ranges, horizontal lines indicate medians, and red markers indicate means. Pathology characterization requires the longest rationales on average, while lesion localization uses the shortest; anomaly detection exhibits the most pronounced upper-tail outliers.

Figure A.3: Word cloud of the generated CoT annotations, with word size proportional to corpus frequency. The dominant terms describe anatomy, imaging modalities, tissue appearance, visual evidence, and spatial relationships.

Final Disposition Category	Traces	Proportion
Accepted without modification (Round 1)	81,172	62.37%
Accepted after limited manual revision	10,997	8.45%
Accepted after iterative regeneration	37,977	29.18%
Total Retained	130,146	100.00%

Appendix

Table A.7: Composition of the final 130,146 retained CoT annotations for MedAD-38K after the iterative refinement process.

Dimension	Agreement	Macro-F1	Cohen’s $\kappa$
Visual Grounding	91.20%	0.865	0.768
Task Relevance	95.60%	0.924	0.872
Answer Support	93.80%	0.895	0.821
No Hallucination	92.50%	0.878	0.795
No Contradiction	94.70%	0.912	0.854
Average	93.56%	0.895	0.822

Appendix

Table A.8: Inter-annotator agreement on 1,000 independently reviewed CoT annotations. Agreement is reported as a percentage; Macro-F1 and Cohen’s

\kappa

are unitless.

Split	Images	Image Ratio	VQA	VQA Ratio
Test	15,360	40.0%	52,025	40.0%
Train-SFT	16,150	42.0%	54,709	42.0%
Train-RL	6,912	18.0%	23,412	18.0%
Training	23,062	60.0%	78,121	60.0%
Total	38,422	100.0%	130,146	100.0%

Appendix

Table A.9: Image-level split of MedAD-38K. All VQA instances associated with the same image remain in one subset.

Dimension	Initial Prompt		Calibrated Prompt
Dimension	Agreement	$\kappa$	Agreement	$\kappa$
Visual Grounding	82.40%	0.615	95.80%	0.892
Task Relevance	86.50%	0.712	97.20%	0.935
Answer Support	84.10%	0.668	96.50%	0.914
No Hallucination	81.20%	0.584	95.40%	0.885
No Contradiction	85.30%	0.695	96.80%	0.921

Appendix

Table B.1: Agreement between MedGemma-4B and human annotations on the held-out calibration set, before and after prompt calibration.

Judge Pair	Agreements	Samples	Rate
GLM-4.6V-Flash vs. InternVL3.5-8B	873	1,000	87.30%
GLM-4.6V-Flash vs. Qwen3-VL-8B-Instruct	909	1,000	90.90%
InternVL3.5-8B vs. Qwen3-VL-8B-Instruct	916	1,000	91.60%
Average	2,698	3,000	89.93%

Appendix

Table B.2: Agreement among the three evaluation judges on 1,000 outputs generated by the four SFT-stage backbone models from randomly sampled MedAD-38K training instances.

Model	Params	Anat.	Anom.	Loc.	Mod.	Path.	Overall
Qwen3.5-0.8B	0.8B	94.22 $\pm$ 0.53	57.88 $\pm$ 0.84	33.74 $\pm$ 0.96	93.45 $\pm$ 0.65	14.93 $\pm$ 2.70	76.43 $\pm$ 0.49
InternVL3.5-1B	1B	95.04 $\pm$ 1.94	50.09 $\pm$ 3.00	33.53 $\pm$ 2.83	89.27 $\pm$ 6.81	15.52 $\pm$ 8.19	73.10 $\pm$ 2.63
Qwen3VL-2B	2B	91.20 $\pm$ 6.27	55.54 $\pm$ 1.67	37.08 $\pm$ 5.74	92.57 $\pm$ 2.44	10.75 $\pm$ 9.13	74.91 $\pm$ 3.34
Qwen2.5VL-3B	3B	78.56 $\pm$ 8.33	50.29 $\pm$ 6.69	30.63 $\pm$ 4.75	78.97 $\pm$ 6.00	11.04 $\pm$ 12.19	64.90 $\pm$ 6.05
MiMo-VL-7B	7B	61.71 $\pm$ 8.46	55.20 $\pm$ 2.15	30.04 $\pm$ 2.94	63.71 $\pm$ 7.87	28.81 $\pm$ 5.55	56.86 $\pm$ 5.47
Qwen2.5VL-7B	7B	75.43 $\pm$ 8.82	56.10 $\pm$ 1.46	26.90 $\pm$ 1.78	82.28 $\pm$ 5.38	15.52 $\pm$ 10.40	66.30 $\pm$ 4.60

Appendix

Table C.1: Detailed MedAD-38K test accuracy over five independent inference passes of each fixed checkpoint, reported as mean

\pm

standard deviation (%). No retraining is performed between passes. Overall is micro-averaged over all applicable VQA instances. ∗ marks medical LMMs and † marks larger models fine-tuned on our training data. Boldface denotes the best result and underlining the second best.

Model	Params	Vis. Ground.	Task Rel.	Ans. Supp.	No Hall.	No Contr.	Prompt A	Consist.	Insuff.
Qwen3.5-0.8B	0.8B	78.56	98.82	81.45	96.83	97.54	4.53	92.12	4.45
InternVL3.5-1B	1B	76.24	97.63	77.82	96.87	96.15	4.45	93.53	0.45
Qwen3-VL-2B	2B	80.56	97.68	82.15	96.82	97.53	4.55	94.84	0.42
Qwen2.5-VL-3B	3B	60.15	96.54	62.52	96.91	97.23	4.13	93.25	2.74
MiMo-VL-7B	7B	50.24	96.51	52.49	94.56	95.55	3.89	94.57	0.47
Qwen2.5-VL-7B	7B	75.42	97.83	76.68	97.16	97.66	4.45	94.17	3.22

Appendix

Table C.2: Main results on the pooled outputs from all five MedAD-38K inference passes. The five dimensions average the three independent judge scores, and Prompt A is their sum on a 0–5 scale; Consist. and Insuff. use the majority-voted Prompt-B verdict. SFT-only rows are the Stage-1 counterparts of the four complete MedAD-R1 models. Vis. Ground.: Visual Grounding; Task Rel.: Task Relevance; Ans. Supp.: Answer Support; No Hall.: No Hallucination; No Contr.: No Contradiction. All metrics except Prompt A are percentages. Higher is better except for Insuff. Boldface marks the best value in each column. ∗ marks a medical LMM and † a larger model fine-tuned on our data.

Dataset	Modality	Anatomy	Images	VQA
ColonDB	Endoscopy	Gastrointestinal	380	1,520
HeadCT	CT	Brain	200	800
EndoTect (Endo)	Endoscopy	Gastrointestinal	200	800
TN3K	Ultrasound	Thyroid	3,493	13,972
NMSC Histopathology	Microscopy	Skin	290	1,160
Total			4,563	18,252

Appendix

Table C.3: Composition of the five source-disjoint external evaluation datasets.

Model	Params	Anatomy ID.	Anomaly Det.	Lesion Loc.	Modality Class.	Pathology Char.	Overall
Qwen3.5-0.8B	0.8B	72.80 $\pm$ 0.97	55.80 $\pm$ 4.87	43.94 $\pm$ 0.98	99.29 $\pm$ 0.27	71.20 $\pm$ 6.79	68.12 $\pm$ 1.25
InternVL3.5-1B	1B	89.26 $\pm$ 2.94	55.82 $\pm$ 7.12	37.40 $\pm$ 5.57	95.73 $\pm$ 7.52	81.20 $\pm$ 6.11	69.81 $\pm$ 4.95
Qwen3-VL-2B	2B	85.88 $\pm$ 10.10	42.60 $\pm$ 3.01	42.26 $\pm$ 9.59	98.21 $\pm$ 1.77	62.00 $\pm$ 17.03	67.35 $\pm$ 5.53
Qwen2.5-VL-3B	3B	45.16 $\pm$ 5.73	39.45 $\pm$ 7.26	31.40 $\pm$ 5.51	87.60 $\pm$ 3.75	60.40 $\pm$ 15.81	51.07 $\pm$ 4.79
MiMo-VL-7B	7B	42.79 $\pm$ 11.25	39.61 $\pm$ 7.48	26.31 $\pm$ 1.23	48.50 $\pm$ 7.87	58.00 $\pm$ 19.06	39.49 $\pm$ 5.86
Qwen2.5-VL-7B	7B	51.31 $\pm$ 10.54	34.87 $\pm$ 8.69	27.22 $\pm$ 2.18	85.77 $\pm$ 7.91	82.20 $\pm$ 11.44	50.12 $\pm$ 5.88

Appendix

Table C.4: External-test accuracy over five independent inference passes of each fixed checkpoint, reported as mean

\pm

standard deviation (%). No retraining is performed between passes. Overall is micro-averaged across all 18,252 applicable VQA instances rather than computed as an unweighted mean of the task columns. Boldface marks the best value in each column. ∗ marks a medical LMM and † a larger model fine-tuned on our data.

Model	Params	Vis. Ground.	Task Rel.	Ans. Supp.	No Hall.	No Contr.	Prompt A	Consist.	Insuff.
Qwen3.5-0.8B	0.8B	72.34	97.72	74.19	97.41	98.20	4.40	88.75	6.76
InternVL3.5-1B	1B	68.96	98.96	70.17	97.09	96.14	4.31	91.53	0.22
Qwen3-VL-2B	2B	78.24	98.93	79.25	97.29	98.65	4.52	94.41	0.18
Qwen2.5-VL-3B	3B	55.17	97.55	56.89	96.91	98.33	4.05	92.01	2.33
MiMo-VL-7B	7B	46.93	97.50	48.58	95.84	97.92	3.87	93.78	0.13
Qwen2.5-VL-7B	7B	69.30	98.79	70.39	98.07	98.72	4.35	91.84	3.79

Appendix

Table C.5: Reasoning-quality results on the pooled outputs from all five external-set inference passes. The five dimensions average the three independent judge scores, and Prompt A is their sum on a 0–5 scale; Consist. and Insuff. use the majority-voted Prompt-B verdict. SFT-only rows are the Stage-1 counterparts of the four complete MedAD-R1 models. The abbreviations and symbols follow Table C.2 ; all metrics except Prompt A are percentages, and lower is better only for Insuff.

Backbone	Setting	Anatomy	Modality	Anomaly	Localization	Pathology	Overall	$\Delta$
Qwen3.5-0.8B	Zero-shot	94.22	93.45	57.88	33.74	14.93	76.43	–
	SFT only	95.11	95.07	82.73	90.68	81.09	90.89	–
	Con-GRPO	98.96	99.57	88.30	91.49	85.57	95.12	+4.23
InternVL3.5-1B	Zero-shot	95.04	89.27	50.09	33.53	15.52	73.10	–
	SFT only	92.58	91.51	76.24	83.61	79.10	86.40	–
	Con-GRPO	97.88	98.51	81.40	90.45	80.85	92.31	+5.91

Appendix

Table C.6: Per-task accuracy for the four backbones under zero-shot, SFT-only, and complete Con-GRPO training. Overall is micro-averaged over all applicable test instances rather than computed as an unweighted mean of the task columns. Boldface marks the best value in each metric column.

Setting	Stage 1 (SFT)	Stage 2 (Con-GRPO)
Training subset	Train-SFT	Train-RL
Epochs	2	1
Training GPUs	6	6 policy + 2 reward
Per-device batch size	8	1
Gradient accumulation	1	2
Effective prompt batch	48	12

Appendix

Table C.7: Optimization settings for the two MedAD-R1 training stages.

Model	Params (B)	TTFT (s)	TPOT (ms)	Tokens/s	E2E (s)	Peak Alloc. (GB)	Peak Reserv. (GB)
Lingshu-7B	7.0	0.0932	25.50	39.22	6.625	16.73	16.98
InternVL3.5-8B	8.0	0.0610	26.40	37.88	6.831	17.18	17.34
Qwen3-VL-8B	8.0	0.2910	29.60	33.78	7.864	17.67	17.86
GLM-4.6V-Flash	9.0	0.0922	30.55	32.73	7.921	20.73	20.88
Llama-3.2-Vision	11.0	0.2845	31.20	32.05	8.267	22.30	22.90
Gemma-4-26B	26.0	0.2261	50.83	19.67	13.238	52.00	52.21

Appendix

Table D.1: Inference efficiency under the fixed-length setting (256 output tokens). TTFT: time to first token. TPOT: time per output token. E2E: end-to-end latency. Peak Alloc. and Peak Reserv. are peak allocated and reserved GPU memory. MedAD-R1 variants are grouped at the bottom. Boldface marks the best value in each column.

Model	Params (B)	TTFT (s)	TPOT (ms)	E2E (s)	Out. Tokens	Peak Alloc. (GB)	Peak Reserv. (GB)
Lingshu-7B	7.0	0.0933	25.50	3.618	138.2	16.73	16.98
InternVL3.5-8B	8.0	0.0612	26.40	4.925	184.3	17.22	17.34
Qwen3-VL-8B	8.0	0.2940	29.60	5.490	175.5	17.71	17.86
GLM-4.6V-Flash	9.0	0.0932	30.55	15.734	512.0 ∗	20.73	20.88
Llama-3.2-Vision	11.0	0.2847	31.20	6.166	188.6	22.30	22.90
Gemma-4-26B	26.0	0.2269	50.83	15.275	295.7	52.05	52.21

Appendix

Table D.2: Inference behavior under the natural setting, where each model stops on its own. End-to-end latency here is governed by output length and is not a controlled speed comparison; see Table D.1 for the fixed-length comparison. Boldface marks the lowest numerical value in each column; end-to-end latency and output length remain descriptive rather than controlled comparisons. ∗ GLM-4.6V-Flash reached the maximum generation limit of 512 tokens because it did not emit an explicit end-of-sequence token in this zero-shot setting.

Case	Gold	Ours	InternVL	Gemma	Huatuo ∗	LLaVA ∗	Lingshu ∗	MedVLM ∗
Liver-mass location	B	B	A	A	A	C	C	C
Thyroid finding	B	B	A	A	A	A	A	A

Appendix

Table E.1: Answer-level summary of the two manually reviewed qualitative cases. ∗ denotes a domain-specific medical LMM. All 12 comparison answers are incorrect under the source-derived labels.

Figure E.1: Lesion-localization example (source-derived answer: B, Center-Region). The annotated finding spans a large portion of the liver and is assigned to the center region by the mask-based five-region rule.

Figure E.2: Thyroid-ultrasound anomaly-detection example (source-derived answer: B, Yes). A focal echotextural abnormality is distinguishable from the surrounding thyroid parenchyma.

Explore similar work

OpenMedReason: Scientific Reasoning Supervision for Medical Vision-Language Models
Jun 10, 2026Negin Baghbanzadeh, Pritam Sarkar, Michael Colacci +6Medical Vision-Language Models Recent Vision-Language Models
York University · Vector Institute · University of British Columbia +5
M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding
Jan 13, 2026Juntao Jiang, Jiangning Zhang, Yali Bi +7Medical Images Diagnostic Benchmark
1Zhejiang University · University of Science and Technology of China · 3East China Normal University +2
MedQA-MM: Shortcuts Behind Medical Visual Reasoning
Sep 3, 2026Benlu Wang, Yifan Zhang, Jiaqing Yu +7Medical Visual Question Answering Multimodal Clinical Data
University of Massachusetts Amherst · 4Yale University · University of Massachusetts Lowell +6

Jun 10, 2026, cs.CVJ/K move · Enter open · S save

OpenMedReason: Scientific Reasoning Supervision for Medical Vision-Language Models

Negin Baghbanzadeh, Pritam Sarkar, Michael Colacci, Abeer Badawi+5

York University · Vector Institute · University of British Columbia+5

Medical Vision-Language Models Recent Vision-Language Models Text Corpora Scientific Discovery

Open paper AskPDF arXiv

High-stakes clinical use of large vision-language models (LVLMs) requires reasoning that is grounded in visual evidence and clinical knowledge, not just correct final answers. We introduce OpenMedReason, a large-scale, open multimodal medical reasoning corpus comprising approximately 450K image-question-answer instances whose reasoning traces are primarily derived from curated biomedical, human-authored scientific articles. OpenMedReason provides high-fidelity supervision beyond synthetic chains of thought, covering diverse medical domain vision modalities such as radiological scans, microscopic images, visible light photographs, charts, and others. We complement it with OpenMedReason-Bench, a held-out benchmark that allows fine-grained evaluation of LVLMs along three complementary axes of capability, including perception, medical knowledge, and rationale, enabling diagnostic evaluation beyond final-answer accuracy. OpenMedReason is a rich training resource that exhibits its effectiveness in both supervised fine-tuning (SFT) and reinforcement-based alignment. Training with OpenMedReason yields a 20% average improvement in VQA accuracy over the base model and achieves performance within 4.2% of the strongest comparable-scale medical LVLMs. Fine-grained performance analysis confirms that the gains are not concentrated in any single axis: OpenMedReason improves perception, medical knowledge, and rationale jointly, and its reasoning traces are preferred over those of the base model in 86.1% of pairwise comparisons. We release the code and dataset at huggingface.co/datasets/neginb/OpenMedReason.

Abstract

Explore similar work

OpenMedReason: Scientific Reasoning Supervision for Medical Vision-Language Models

M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding

MedQA-MM: Shortcuts Behind Medical Visual Reasoning