English(EN) Are Linguistic and Arithmetic Circuits Dissociated in LLMs?

研究表明大型语言模型使用独立的语言和数学电路

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-21 04:00

一项新发表在arXiv上的研究调查了大型语言模型（LLMs）中的语言和算术处理是否利用独立的神经网络电路。研究人员使用机械可解释性技术分析了五个LLM，发现电路相似性主要由任务领域（语言与算术）决定，而不是由共享词汇或句法相似性决定。这表明LLM可能拥有处理不同类型信息的模块化组织。 AI

影响通过理解模块化处理，为更专业、更高效的LLM架构提供了可能性。

排序理由发表在arXiv上的研究论文，详细介绍了关于LLM内部工作原理的发现。[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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 发表在arXiv上的研究论文，详细介绍了关于LLM内部工作原理的发现。[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, model release; 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: 2 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

arXiv cs.CL TIER_1 English(EN) · Riku Kisako, Tatsuki Kuribayashi, Ryohei Sasano · 2026-10-21 04:00

大型语言模型中的语言和算术电路是否分离？

arXiv:2610.27790v1 Announce Type: new Abstract: Large language models (LLMs) exhibit both knowledge of language, rendered by, for example, grammatical judgment ability, and abilities to perform tasks through language, such as math-word problem solving. Motivated by neurolinguisti…