Author

Kyle Lo

h-index 3 View on Semantic Scholar

We have 1 of 7 papers

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.

Preprint Jul 2026

Pretraining Data Can Be Poisoned through Computational Propaganda

This work demonstrates the importance of estimating whether poison injections are included in pretraining data, and establishes third-party webpage content as a possible vector for attacking language model pretraining.

Victoria Graf, Hanna Hajishirzi, Noah A. Smith et al. · 0 citations