# Wasserstein Equilibrium Decoding for Reliable Medical Visual Question Answering

arXiv: https://arxiv.org/abs/2605.18313 · HTML: https://mlsanity.com/paper/2605.18313/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 18 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 20 of 20)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [PathVQA: 30000+ Questions for Medical Visual Question Answering](https://mlsanity.com/paper/2003.10286/) (2020)
- [Med-Flamingo: a Multimodal Medical Few-shot Learner](https://mlsanity.com/paper/2307.15189/) (2023)
- [Self-Alignment Pretraining for Biomedical Entity Representations](https://mlsanity.com/paper/2010.11784/) (2020)
- [Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?](https://mlsanity.com/paper/2402.18272/) (2024)
- [Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review](https://mlsanity.com/paper/2403.02469/) (2024)
- [Medical Visual Question Answering: A Survey](https://mlsanity.com/paper/2111.10056/) (2021)
- [Isambard-AI: a leadership class supercomputer optimised specifically for Artificial Intelligence](https://mlsanity.com/paper/2410.11199/) (2024)
- [The Consensus Game: Language Model Generation via Equilibrium Search](https://mlsanity.com/paper/2310.09139/) (2023)
- [The Rise of Small Language Models in Healthcare: A Comprehensive Survey](https://mlsanity.com/paper/2504.17119/) (2025)
- [Memoryless Algorithmic Collusion: Sure to Fail, Slow to Fall](https://mlsanity.com/paper/2409.01147/) (2024)
- [Towards Edge General Intelligence via Large Language Models: Opportunities and Challenges](https://mlsanity.com/paper/2410.18125/) (2024)
- [Algorithmic collusion in a two-sided market: A rideshare example](https://mlsanity.com/paper/2405.02835/) (2024)

## Abstract (arXiv)

Small vision-language models (2-8B) are well-suited for clinical deployment due to privacy constraints, limited connectivity, and low-latency requirements favouring on-device or on-premise inference. However, their limited capacity exacerbates the generation of plausible but incorrect outputs. We extend game-theoretic decoding, previously restricted to text-only, closed-ended NLP tasks, to vision-language models for open-ended Medical VQA. We introduce a semantically aware Wasserstein stopping criterion that replaces lexical order matching, enabling convergence based on semantic consensus among near-synonymous candidate answers and avoiding unnecessary iterations caused by clinically equivalent ranking swaps. On VQA-RAD and PathVQA, we obtain consistent, statistically significant improvements over greedy and discriminative baselines. On VQA-RAD, we improve Qwen3-VL-2B by +3.5 percentage points (p < 0.01), surpassing the greedy 4B model, with similar trends at larger scales. On PathVQA, Gemma-3-4B with BDG matches MedGemma-4B under greedy decoding despite no domain-specific fine-tuning. At accuracy parity with classic BDG, the Wasserstein criterion reduces average convergence iterations by approximately 20%, improving inference efficiency while preserving the game-theoretic equilibrium behaviour. Code is available at https://github.com/luca-hagen/ Wasserstein-BDG-medical-VQA.