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

The paper investigates how metaphoric concepts are encoded in large language models (LLMs) by applying mechanistic interpretability methods to identify causal subspaces across various architectures and sizes. It demonstrates that manipulating these subspaces allows steering of metaphor-related outputs on both classification and generation tasks, effectively controlling the metaphoricity of LLM responses.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• llms
• safety