131

Large Language Models Encode Semantics in Low-Dimensional Linear Subspaces

Main:12 Pages
11 Figures
Bibliography:6 Pages
4 Tables
Appendix:9 Pages
Abstract

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. \baturay{However, it remains unclear to what extent LLMs internally organize representations related to semantic understanding. To investigate this, we conduct a large-scale empirical study of hidden states in transformer-based LLMs, analyzing 11 decoder-only models across 6 scientific topics and 12 layers each. We find that high-level semantic information consistently lies in low-dimensional subspaces that form linearly separable representations across distinct domains. This separability becomes more pronounced in deeper layers and under prompts that trigger structured reasoning or alignment behaviors\unicodex2013\unicode{x2013}even when surface content is unchanged. This geometry enables simple yet effective causal interventions in hidden space; for example, reasoning patterns like chain-of-thought can be captured by a single vector direction. Together, these findings support the development of geometry-aware tools that operate directly on latent representations to detect and mitigate harmful or adversarial content, using methods such as transport-based defenses that leverage this separability. As a proof of concept, we demonstrate this potential by training a simple MLP classifier as a lightweight latent-space guardrail, which detects adversarial and malicious prompts with high precision.

View on arXiv
Comments on this paper