English(EN) A Circuit for Plural Reference: How LLMs Represent and Retrieve Singular and Plural Entities

大型语言模型复数指代机制受审视

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-04 04:00

研究人员调查了大型语言模型（LLMs）如何处理复数指代，特别是它们如何表征和检索单数与复数实体。该研究利用机制可解释性和注意力模式分析，识别出负责共指信息的特定注意力头，识别复数指代，并预测代词。研究结果表明，大型语言模型在复数代词方面与人类偏好一致，尤其是在实体本体上相似并通过“和”连接时。 AI

影响为共指消解中的大型语言模型推理能力提供了见解，可能提高其对复杂语言结构的理解。

排序理由该集群包含一篇详细介绍大型语言模型机制研究的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

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: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍大型语言模型机制研究的论文。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Anh Danh, Rick Nouwen, Massimo Poesio · 2026-09-04 04:00

复数指代电路：大型语言模型如何表征和检索单复数实体

arXiv:2609.03687v1 Announce Type: new Abstract: Coreference resolution is an important task in contextual reasoning. In this paper, we investigate the mechanism for representing and retrieving singular and plural entities for plural reference. We use a combination of mechanistic …

本文如何被排名

报道来源 [1]

复数指代电路：大型语言模型如何表征和检索单复数实体

相关实体

相关话题