arXiv cs.AI· Jungwoo Oh, Hyunseung Chung, Junhee Lee, Min-Gyu Kim, Hangyul Yoon, Ki Seong Lee, Youngchae Lee, Muhan Yeo, Edward Choi·· 14 小时前AI 评分26
ECG-Reasoning-Benchmark：评估 MLLM 心电图临床推理能力的基准
ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation
AI 导读
研究者提出 ECG-Reasoning-Benchmark，一个含 6400 多个样本的多轮评测框架，覆盖 17 种核心心电图诊断，用于检验多模态大模型是否真正逐步推理。评测显示，当前 SOTA 模型虽能检索诊断标准，却难以维持完整推理链，主要失败在于无法把心电图发现对应到信号中的实际视觉证据。
正文 · 原文
Abstract:While Multimodal Large Language Models (MLLMs) show promising performance in automated electrocardiogram interpretation, it remains unclear whether they perform actual step-by-step reasoning or just rely on superficial visual cues. To investigate this, we introduce ECG-Reasoning-Benchmark, a novel multi-turn evaluation framework comprising over 6,400 samples to systematically assess step- by-step reasoning across 17 core ECG diagnoses. Our comprehensive evaluation of state-of-the-art models reveals a systematic shortfall in executing multi-step logical deduction. Although models possess the medical knowledge to retrieve clinical criteria for a diagnosis, they exhibit consistently low success rates in maintaining a complete reasoning chain, primarily failing to ground the corresponding ECG findings to the actual visual evidence in the ECG signal. These results demonstrate that current MLLMs bypass actual visual interpretation, highlighting a limitation in their visual grounding capabilities and motivating robust, reasoning-centric medical AI. The code and data are available at this https URL.
| Comments: | Accepted at NeurIPS 2026 Evaluations & Datasets Track |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2603.14326 [cs.LG] |
| (or arXiv:2603.14326v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2603.14326 arXiv-issued DOI via DataCite |
Submission history
From: Jungwoo Oh [view email]
[v1]
Sun, 15 Mar 2026 11:09:38 UTC (4,770 KB)
[v2]
Wed, 28 Oct 2026 08:34:51 UTC (4,878 KB)
来源：arXiv cs.AI · arxiv.org