The SLSO framework uses iterative structured output generation, consistency checks, and regeneration to improve GPT-VLM accuracy on jaw cyst findings in panoramic radiographs compared to standard chain-of-thought prompting.
arXiv:2503.02157 (2025)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
A dual-side evidence-injection method using ROI-guided modulation and semantic token mapping improves medical MLLM close-ended accuracy by up to 6% and cuts open-ended hallucinations by 35% across 5 datasets.
citing papers explorer
-
Generating Findings for Jaw Cysts in Dental Panoramic Radiographs Using a GPT-Based VLM: A Preliminary Study on Building a Two-Stage Self-Correction Loop with Structured Output (SLSO) Framework
The SLSO framework uses iterative structured output generation, consistency checks, and regeneration to improve GPT-VLM accuracy on jaw cyst findings in panoramic radiographs compared to standard chain-of-thought prompting.
-
Synergistic Perception-Reasoning Governance: Grounding Medical MLLMs with Verifiable Anatomical Evidence
A dual-side evidence-injection method using ROI-guided modulation and semantic token mapping improves medical MLLM close-ended accuracy by up to 6% and cuts open-ended hallucinations by 35% across 5 datasets.