The Geometry of Metaphor: Probing and Steering Metaphor Representations in Large Language Models

cs.CL cs.AI Shihui Li, Mette Andersen, Martha Lewis · Oct 22, 2026

What it does

Metaphor is a crucial aspect of human cognition. As such, we would like to understand how it is represented in large language models (LLMs) and how it might be controlled.

Why it matters

We show that we are able to steer output on classification tasks across different parts of speech. We are also able to steer output on generation tasks, indicating that these techniques can be used to control the metaphoricity of LLM...

Review status

The review hit a snag and will retry automatically. The abstract is still available below.

Community signal

0 up · 0 down

AI Review Review failed

Review failed. It will be retried automatically.

Abstract

Metaphor is a crucial aspect of human cognition. As such, we would like to understand how it is represented in large language models (LLMs) and how it might be controlled. We use mechanistic interpretability techniques to identify causal subspaces in a range of LLMs covering different architectures and sizes. We show that we are able to steer output on classification tasks across different parts of speech. We are also able to steer output on generation tasks, indicating that these techniques can be used to control the metaphoricity of LLM output.

Challenge the Review

Pick a starting point or write your own. Challenges run in the background, so you can keep reading while the AI investigates.

Challenges are public to read, but only signed-in members can post them. Your challenge text is stored with your account for moderation, but usernames are not shown in the public thread.

No challenges yet. Disagree with the review? Ask the AI to revisit a specific claim.