No AI summary available for this article.
Why It Matters
Reasoning models often act as if they pursue goals, but their efforts are not always directed toward what users intend, sometimes leading them to pursue unintended outcomes.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Reasoning models often act as if they pursue goals, but their efforts are not always directed toward what users intend, sometimes leading them to pursue unintended outcomes. Previous work has examined how models may internally track their progress toward their goals through a "value axis." We study whether changing such a signal can retarget the model's search toward a different goal. We test value transplant: at each token, we shift the host model's activation along a candidate value axis by the donor-host difference in value coordinates (multiplied by a large scalar), aiming to redirect the...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.34056v1 · Indexed 42 minutes ago