按年被提到
20242024 · 5 次2026
大模型与语言模型›词向量与预训练模型·arXiv:2406.01506 · cs.CL

The Geometry of Categorical and Hierarchical Concepts in Large Language Models

Kiho Park, Yo Joong Choe, Yibo Jiang, Victor Veitch · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 4 人首次 2024-06-04 · 最近 2024-07-10
4不同的人
2活跃月份
5讨论串
19被引(OpenAlex)
arXiv 摘要(候选层不写导读)

The linear representation hypothesis is the informal idea that semantic concepts are encoded as linear directions in the representation spaces of large language models (LLMs). Previous work has shown how to make this notion precise for representing binary concepts that have natural contrasts (e.g., {male, female}) as directions in representation space. However, many natural concepts do not have natural contrasts (e.g., whether the output is about an animal). In this work, we show how to extend the formalization of the linear representation hypothesis to represent features (e.g., is_animal) as vectors. This allows us to immediately formalize the representation of categorical concepts as polytopes in the representation space. Further, we use the formalization to prove a relationship between the hierarchical structure of concepts and the geometry of their representations. We validate these theoretical results on the Gemma and LLaMA-3 large language models, estimating representations for 900+ hierarchically related concepts using data from WordNet.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论davedx · 2024-07

“This seems highly relevant: https://arxiv.org/abs/2406.01506 > In this paper, we study the two foundational questions in this area. First, how are categorical concepts, such as {'mammal', 'bird', 'reptile', 'fish'}, represented? Second, how are hierarchical relations between concepts encoded? For example, how is the fact that 'dog' is a kind of 'mammal' …”

Knowledge Graphs in RAG: Hype vs. Ragas Analysis原评论 ↗
被提交为 story · 4 次