English

Flexible Model Interpretability through Natural Language Model Editing

Computation and Language 2023-11-21 v1 Artificial Intelligence

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.

Keywords

Cite

@article{arxiv.2311.10905,
  title  = {Flexible Model Interpretability through Natural Language Model Editing},
  author = {Karel D'Oosterlinck and Thomas Demeester and Chris Develder and Christopher Potts},
  journal= {arXiv preprint arXiv:2311.10905},
  year   = {2023}
}

Comments

Extended Abstract -- work in progress. BlackboxNLP2023

R2 v1 2026-06-28T13:24:48.371Z