# Sum-of-Checks: Structured Reasoning for Surgical Safety with Large Vision-Language Models

arXiv: https://arxiv.org/abs/2604.22156 · HTML: https://mlsanity.com/paper/2604.22156/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 24 Apr 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 8 of 8)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [SurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery](https://mlsanity.com/paper/2304.09974/) (2023)
- [EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery](https://mlsanity.com/paper/2501.11347/) (2025)
- [Surgical Action Triplet Detection by Mixed Supervised Learning of Instrument-Tissue Interactions](https://mlsanity.com/paper/2307.09548/) (2023)
- [The Endoscapes Dataset for Surgical Scene Segmentation, Object Detection, and Critical View of Safety Assessment: Official Splits and Benchmark](https://mlsanity.com/paper/2312.12429/) (2023)
- [The SAGES Critical View of Safety Challenge: A Global Benchmark for AI-Assisted Surgical Quality Assessment](https://mlsanity.com/paper/2509.17100/) (2025)

## Abstract (arXiv)

Purpose: Accurate assessment of the Critical View of Safety (CVS) during laparoscopic cholecystectomy is essential to prevent bile duct injury, a complication associated with significant morbidity and mortality. While large vision-language models (LVLMs) offer flexible reasoning, their predictions remain difficult to audit and unreliable on safety-critical surgical tasks. Methods: We introduce Sum-of-Checks, a framework that decomposes each CVS criterion into expert-defined reasoning checks reflecting clinically relevant visual evidence. Given a laparoscopic frame, an LVLM evaluates each check, producing a binary judgment and justification. Criterion-level scores are computed via fixed, weighted aggregation of check outcomes. We evaluate on the Endoscapes2023 benchmark using three frontier LVLMs, comparing against direct prompting, chain-of-thought, and sub-question decomposition, each with and without few-shot examples. Results: Sum-of-Checks improves average frame-level mean average precision by 12--14% relative to the best baseline across all three models and criteria. Analysis of individual checks reveals that LVLMs are reliable on observational checks (e.g., visibility, tool obstruction) but show substantial variability on decision-critical anatomical evidence. Conclusion: Structuring surgical reasoning into expert-aligned verification checks improves both accuracy and transparency of LVLM-based CVS assessment, demonstrating that explicitly separating evidence elicitation from decision-making is critical for reliable and auditable surgical AI systems. Code is available at https://github.com/BrachioLab/SumOfChecks.