Research
Option-Aware Retrieval and Task-Specific VLM Adaptation for Medical VQA
arXiv:2609.15530v1 Announce Type: new Abstract: We describe our submission to the MedReason 2026 challenge, covering multiple-choice (MCQ) and open-ended (OE) medical visual question answering (VQA) u
arXiv:2609.15530v1 Announce Type: new Abstract: We describe our submission to the MedReason 2026 challenge, covering multiple-choice (MCQ) and open-ended (OE) medical visual question answering (VQA) under fully offline, containerized inference. Our first finding is that MCQ retrieval must compare answer semantics rather than answer labels: labels are independently assigned per question, so copying a retrieved neighbor's label transfers no useful information, whereas scoring each current option's text against correct-answer text from similar training cases raises retrieval-only accuracy from 20.0% to 57.5% on a 200-case retrieval-excluded development holdout. Our second finding attributes the submitted system's accuracy: holding the task-specific MCQ Low-Rank Adaptation (LoRA) adapter fixed and varying the number (k) of in-prompt retrieved examples changes accuracy by at most one case --- 187/200 (93.5%) at both (k=0) and the adapter's training-time (k=1), 188/200 (94.0%) at the packaged runtime's default (k=3) --- and the submitted confidence-gated override adds no net accuracy on top of (k=3), selecting the VLM in 198/200 cases. With the final MCQ adapter fixed, retrieval changes accuracy by at most one case, and gating provides no net gain. On 20 OE cases, token-F1 and RaTEScore~ite{zhao2024ratescore} decrease as (k) grows, but paired sign tests on token-F1 differences are nonsignificant ((p ge 0.29)); a single-annotator comparison found 6/20 wrong-anchor errors for the final configuration and 14/20 for an earlier configuration that jointly differed in routing, adapter, and prompting. The system reaches 94.0% MCQ accuracy on the development holdout and 93.20% on the organizer's official pre-evaluation, versus 29.43% for the off-the-shelf reference baseline, while both of the organizer's open-ended scores are lower than that baseline's (ground-truth agreement 1.245 versus 1.588, visual accuracy 1.995 versus 2.696, each out of 4).
Related
- Location-Aware Pretraining for Medical Difference Visual Question Answering
- ViSAR: Training-Free Adaptive-k Retrieval for Visual Document Question Answering
- Frequency-Domain Dual-Branch Fusion for Medical Visual Question Answering
Source: arXiv cs.AI | 2026-09-15