vix.ing · top · new · best · stats · spec

Transforming Hidden States into Binary Semantic Features

2024/09/29 by Tomáš Musil, Musil, Tomáš, David Mareček +1
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Semantic Web and Ontologies

paper · pdf · doi:10.48550/arxiv.2409.19813

openalex publication_date 2024/09/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Large language models follow a lineage of many NLP applications that were directly inspired by distributional semantics, but do not seem to be closely related to it anymore. In this paper, we propose to employ the distributional theory of meaning once again. Using Independent Component Analysis to overcome some of its challenging aspects, we show that large language models represent semantic features in their hidden states.

Related