Back to Search
Start Over
Flexible Model Interpretability through Natural Language Model Editing
- Publication Year :
- 2023
-
Abstract
- Model interpretability and model editing are crucial goals in the age of large language models. Interestingly, there exists a link between these two goals: if a method is able to systematically edit model behavior with regard to a human concept of interest, this editor method can help make internal representations more interpretable by pointing towards relevant representations and systematically manipulating them.<br />Comment: Extended Abstract -- work in progress. BlackboxNLP2023
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2311.10905
- Document Type :
- Working Paper