# Measuring and Improving Complex-Atomic Answer Consistency in Endoscopic VQA

arXiv: https://arxiv.org/abs/2607.17834 · HTML: https://mlsanity.com/paper/2607.17834/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 27 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Builds on (most cited first, 23 of 23)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [PathVQA: 30000+ Questions for Medical Visual Question Answering](https://mlsanity.com/paper/2003.10286/) (2020)
- [SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering](https://mlsanity.com/paper/2102.09542/) (2021)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning](https://mlsanity.com/paper/2506.07044/) (2025)
- [Medical Visual Question Answering: A Survey](https://mlsanity.com/paper/2111.10056/) (2021)
- [FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language Models](https://mlsanity.com/paper/2311.01477/) (2023)
- [Kvasir-VQA: A Text-Image Pair GI Tract Dataset](https://mlsanity.com/paper/2409.01437/) (2024)
- [EndoBench: A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysis](https://mlsanity.com/paper/2505.23601/) (2025)
- [Kvasir-VQA-x1: A Multimodal Dataset for Medical Reasoning and Robust MedVQA in Gastrointestinal Endoscopy](https://mlsanity.com/paper/2506.09958/) (2025)
- [SurgViVQA: Temporally-Grounded Video Question Answering for Surgical Scene Understanding](https://mlsanity.com/paper/2511.03325/) (2025)
- [EndoCogniAgent: Closed-Loop Agentic Reasoning with Self-Consistency Validation for Endoscopic Diagnosis](https://mlsanity.com/paper/2508.07292/) (2025)
- [SOrT-ing VQA Models : Contrastive Gradient Learning for Improved Consistency](https://mlsanity.com/paper/2010.10038/) (2020)
- [Gastric-X: A Multimodal Multi-Phase Benchmark Dataset for Advancing Vision-Language Models in Gastric Cancer Analysis](https://mlsanity.com/paper/2603.19516/) (2026)
- [Multimodal AI for Gastrointestinal Diagnostics: Tackling VQA in MEDVQA-GI 2025](https://mlsanity.com/paper/2507.14544/) (2025)

## Abstract (arXiv)

Endoscopic visual question answering (VQA) increasingly asks complex questions that combine several endoscopic answer components rather than isolated factual queries. Such complex answers may be scored as correct even when the same model fails on associated atomic questions. We introduce EndoCA, a paired complex-atomic answer consistency benchmark for evaluating whether complex answers remain consistent with same-image atomic answers. EndoCA contains two suites: EndoCA-Core evaluates compact question-complexity patterns commonly seen in practical endoscopic VQA, and EndoCA-Diagnostic supports controlled analysis across increasing question complexity. We evaluate 11 VLMs spanning open, medical, endoscopy-adapted, and closed-source models on EndoCA. Some VLMs achieve high complex-answer accuracy, yet their atomic-answer accuracy and complex-atomic answer consistency remain substantially lower. To reduce this complex-atomic inconsistency, we introduce Atomic-Support Reconciliation (ASR), a training-free mechanism that uses model-generated atomic answers as contextual premises for answer revision and consistency-guided selective answering. On four selected publicly available models, ASR-Revise improves paired complex-atomic correctness with modest changes in complex-answer accuracy, while ASR-Selective improves accuracy on answered cases by allowing the model to abstain from less reliable cases. Together, EndoCA and ASR provide a consistency-aware benchmark and a training-free mechanism for answer reconciliation and selective answering in endoscopic VQA.