English(EN) Detecting Differences Is Not Understanding Structure: Large Language Models Fail at Graph Isomorphism

大语言模型在图同构测试中失败，揭示其缺乏结构理解能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 04:00

一篇新发表在arXiv上的研究论文表明，尽管大语言模型（LLMs）在相关任务上取得了高准确率，但它们并未真正理解图同构。研究发现，当节点标签被置换时，LLMs无法识别同构图，这表明它们依赖于表面模式而非抽象结构推理。这种缺乏置换不变性的现象凸显了LLMs在拓扑理解方面的根本性局限。 AI

影响凸显了LLM推理能力的根本性差距，表明当前模型可能不适用于需要深度结构理解的任务。

排序理由一篇发表在arXiv上的研究论文，详细阐述了大语言模型的局限性。 [lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 10 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 一篇发表在arXiv上的研究论文，详细阐述了大语言模型的局限性。 [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

arXiv cs.CL TIER_1 English(EN) · Kumar Thushalika, Sukumar Kishanthan, Asela Hevapathige · 2026-10-27 04:00

检测差异并非理解结构：大型语言模型无法处理图同构问题

arXiv:2606.09484v2 Announce Type: replace Abstract: Large language models (LLMs) have shown impressive performance on diverse reasoning tasks, yet their capacity for structural reasoning in graphs remains unclear. We investigate whether LLMs can genuinely understand graph isomorp…