English

Identifying Linear Relational Concepts in Large Language Models

Computation and Language 2024-04-02 v2 Artificial Intelligence

Abstract

Transformer language models (LMs) have been shown to represent concepts as directions in the latent space of hidden activations. However, for any human-interpretable concept, how can we find its direction in the latent space? We present a technique called linear relational concepts (LRC) for finding concept directions corresponding to human-interpretable concepts by first modeling the relation between subject and object as a linear relational embedding (LRE). We find that inverting the LRE and using earlier object layers results in a powerful technique for finding concept directions that outperforms standard black-box probing classifiers. We evaluate LRCs on their performance as concept classifiers as well as their ability to causally change model output.

Keywords

Cite

@article{arxiv.2311.08968,
  title  = {Identifying Linear Relational Concepts in Large Language Models},
  author = {David Chanin and Anthony Hunter and Oana-Maria Camburu},
  journal= {arXiv preprint arXiv:2311.08968},
  year   = {2024}
}

Comments

To be published in NAACL 2024

R2 v1 2026-06-28T13:22:05.849Z