Author

M. Farahani

View on Semantic Scholar

1 paper 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.

#natural language process... Jan 2026

To Copy or Not to Copy: Copying Is Easier to Induce Than Recall

Mechanistic analyses of attention routing, MLP contributions, and layer-wise probability trajectories reveal an asymmetry: inducing copying is an easy ``reactivation''process that can be triggered at different locations in the input, while restoring recall is a ``suppression''process that is more fragile and strongly tied to object-token interventions.

M. Farahani, Franziska Penzkofer, Richard Johansson · arXiv.org · 1 citation