---
title: "KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.24730v1"
permalink: "https://feed.astralor.com/items/itm_4c9ff787b58e8425b95de25a"
published: "2026-07-27T17:57:02.000Z"
score: 79
channel: "ai"
tags: ["KANEx","Kolmogorov-Arnold Networks","MIMIC-CXR","Vision-Language Models","Medical Explainability"]
---

# KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability

## AI commentary

> This paper is notable for bridging KAN's theoretical interpretability with practical medical applications. For researchers in trustworthy AI and medical imaging, the KAN-Map heatmap approach and VLM grounding method offer valuable references. Specifically, for algorithm engineers, KAN-Map provides a gradient-free visualization alternative; for clinical AI product managers, it demonstrates a technical path to improve model explanation trustworthiness.

## At a glance

Computer vision models excel in medical applications, but their black-box nature undermines clinician trust. Existing systems pair chest X-ray classifiers with Vision-Language Models (VLMs) for natural-language explanations, yet fail to address the underlying opacity. We propose KANEx, the first framework leveraging the symbolic transparency of Kolmogorov-Arnold Networks (KANs) to ground VLM reasoning, and introduce KAN-Map, a heatmap method derived directly from KANs. On MIMIC-CXR, KAN-based architectures improve semantic similarity and saliency map faithfulness over ResNet/ViT baselines, boosting visual localization and downstream reasoning quality by 10%. Our findings suggest grounding explanations in mathematically interpretable units is a necessary step toward trustworthy medical AI.

## Key points

- KANEx is the first framework to leverage symbolic interpretability of KANs to ground VLM reasoning.
- KAN-Map generates heatmaps directly from KAN models without gradient approximations.
- On MIMIC-CXR, KAN architectures improve semantic similarity and saliency map faithfulness, boosting visual localization and reasoning quality by 10%.

## Full text

Computer vision models have become highly effective for medical applications, yet their black-box nature continues to undermine clinician trust. In clinical workflows, chest X-ray classifiers are increasingly paired with Vision-Language Models (VLMs) to generate natural-language explanations. However, these systems add linguistic fluency without addressing the underlying opacity of the visual model. With the emergence of Kolmogorov-Arnold Networks (KANs), whose spline-based components provide inherently interpretable functional units, we investigate whether this architectural transparency can be leveraged to produce more trustworthy textual explanations. We introduce KANEx, the first ever framework that leverages the symbolic transparency of KANs to ground VLM reasoning. This interpretability also made it possible to design KAN-Map, a novel heatmap generation method derived directly from KAN models rather than gradient approximations. We feed these grounded contexts into downstream VLMs for enhanced explainability. Benchmarked on the MIMIC-CXR dataset, we demonstrate that KAN-based architectures with ResNet/ViT baselines demonstrate improved semantic similarity while producing significantly more faithful saliency maps. KAN architectures improve visual localization and downstream reasoning quality by 10%. Our findings suggest that grounding linguistic explanations and visual attributions in mathematically interpretable units is a necessary step toward trustworthy medical AI.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_4c9ff787b58e8425b95de25a