
LQ
Lucia Quirke, Louis Jaburi, David Johnston, William Z. Li, Gon\c{c}alo Paulo, Guillaume Martres, Girish Gupta, Nora Belrose, Stella Biderman
· 1 min read
ResearcharXiv cs.LG
Bergson: An Open Source Library for Data Attribution
arXiv:2606.11660v4 Announce Type: replace
Abstract: Data attribution is a promising field in interpretability that aims to explain model behavior through the influence of its training data, with applications including debugging undesirable model behavior and training dataset curation. However, significant engineering effort is required to perform it at scale, and many cutting edge techniques lack open-source tooling and support. 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. The library natively supports on-disk gradient stores and multi-node distributed training, and provides quality of life tools for researchers. Finally, we introduce the first open-source implementations of three leading data attribution methods: MAGIC, SOURCE, and TrackStar. The library is available at https://github.com/EleutherAI/bergson .
Original source
This story was published by arXiv cs.LG and written by Lucia Quirke, Louis Jaburi, David Johnston, William Z. Li, Gon\c{c}alo Paulo, Guillaume Martres, Girish Gupta, Nora Belrose, Stella Biderman. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


