Author

Nora Belrose

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

The Unequal Influence of Bad Advice: Using Training Data Attribution to Modulate Emergent Misalignment

This work uses training data attribution to quantitatively estimate how much each harmful example contributes to EM and benchmark the quality of the attribution via retraining -- a sound attribution score should enable us to enhance or attenuate EM by filtering data on that score.

Gonçalo Paulo, Louis Jaburi, Nora Belrose et al. · 1 citation

#machine learning Jun 2026

Bergson: An Open Source Library for Data Attribution

Bergson is an open source library that aims to enable faster progress in the field by providing a host of techniques that scale to very large language models and pre-training datasets, and provides quality of life tools for researchers.

Lucia Quirke, Louis Jaburi, David O. Johnston et al. · arXiv.org · 0 citations