0

Identifying Linear Relational Concepts in Large Language Models

A method called linear relational concepts (LRC) is introduced to find concept directions in the latent space of transformer language models, enabling effective classification and causal influence on model outputs.

Year
2023
Venue
arXiv 2023
Authors
3
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2311.08968v2ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

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.

Authors

3