# CheXPO: Preference Optimization for Chest X-ray VLMs with Counterfactual Rationale

arXiv: https://arxiv.org/abs/2507.06959 · HTML: https://mlsanity.com/paper/2507.06959/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 24 of its 52 references that are in the map.
- First posted on arXiv 9 Jul 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)
- LLM alignment / RLHF / preference optimisation / [Medical LLM alignment](https://mlsanity.com/alignment/medical-llm-alignment/)

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation](https://mlsanity.com/paper/2311.17911/) (2023)
- [Med-Flamingo: a Multimodal Medical Few-shot Learner](https://mlsanity.com/paper/2307.15189/) (2023)
- [HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale](https://mlsanity.com/paper/2406.19280/) (2024)
- [Aligning Modalities in Vision Large Language Models via Preference Fine-tuning](https://mlsanity.com/paper/2402.11411/) (2024)
- [ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts](https://mlsanity.com/paper/2312.00784/) (2023)
- [Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation](https://mlsanity.com/paper/2303.10323/) (2023)
- [Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training](https://mlsanity.com/paper/2209.07098/) (2022)
- [METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens](https://mlsanity.com/paper/2304.02211/) (2023)
- [Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training](https://mlsanity.com/paper/2105.11333/) (2021)
- [Chest ImaGenome Dataset for Clinical Reasoning](https://mlsanity.com/paper/2108.00316/) (2021)
- [Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key](https://mlsanity.com/paper/2501.09695/) (2025)
- [Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators](https://mlsanity.com/paper/2406.13415/) (2024)
- [Describing and Localizing Multiple Changes with Transformers](https://mlsanity.com/paper/2103.14146/) (2021)
- [Expert Knowledge-Aware Image Difference Graph Representation Learning for Difference-Aware Medical Visual Question Answering](https://mlsanity.com/paper/2307.11986/) (2023)
- [Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples](https://mlsanity.com/paper/2502.09650/) (2025)
- [Biomedical Visual Instruction Tuning with Clinician Preference Alignment](https://mlsanity.com/paper/2406.13173/) (2024)
- [STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering](https://mlsanity.com/paper/2406.19973/) (2024)
- [MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization](https://mlsanity.com/paper/2412.06141/) (2024)

## Built on by (most cited first, 5 of 5)

- [Enhancing Radiology Report Generation and Visual Grounding using Reinforcement Learning](https://mlsanity.com/paper/2512.10691/) (2025)
- [CheXPO-v2: Preference Optimization for Chest X-ray VLMs with Knowledge Graph Consistency](https://mlsanity.com/paper/2512.17213/) (2025)
- [Positive-Unlabeled Preference Optimization For Chest X-ray Report Generation](https://mlsanity.com/paper/2608.05341/) (2026)
- [Linguistically-Aligned and Visually-Grounded Preference Optimization for Clinically-Augmented Medical Report Generation](https://mlsanity.com/paper/2608.08494/) (2026)
- [Counterfactual Anatomy-guided Spatial-Temporal Decoding for Annotation-Free Hallucination Mitigation in Medical VLMs](https://mlsanity.com/paper/2608.17427/) (2026)

## Abstract (arXiv)

Vision-language models (VLMs) are prone to hallucinations that critically compromise reliability in medical applications. While preference optimization can mitigate these hallucinations through clinical feedback, its implementation faces challenges such as clinically irrelevant training samples, imbalanced data distributions, and prohibitive expert annotation costs. To address these challenges, we introduce CheXPO, a Chest X-ray Preference Optimization strategy that combines confidence-similarity joint mining with counterfactual rationale. Our approach begins by synthesizing a unified, fine-grained multi-task chest X-ray visual instruction dataset across different question types for supervised fine-tuning (SFT). We then identify hard examples through token-level confidence analysis of SFT failures and use similarity-based retrieval to expand hard examples for balancing preference sample distributions, while synthetic counterfactual rationales provide fine-grained clinical preferences, eliminating the need for additional expert input. Experiments show that CheXPO achieves 8.93% relative performance gain using only 5% of SFT samples, reaching state-of-the-art performance across diverse clinical tasks and providing a scalable, interpretable solution for real-world radiology applications.