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.
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