We have 4 of 211 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.
No post-training method achieves all three properties the authors would want from safe alignment at once: refusal that isn't concentrated in a few fragile components, safety gains that don't cost general capability, and safety behavior correctable through small, targeted edits.
It is shown that harmful-refusal directions are task-agnostic and can be captured by a single global vector, whereas over-refusal directions are task-dependent: they reside within the benign task-representation clusters, vary across tasks, and span a higher-dimensional subspace.
A thematic analysis on open ended questions posed to participants after being led by either a human or CUI based leader on a collaborative task revealed five key themes around how they perceived the leader they were interacting with, highlighting key considerations designers should consider when creating such collabora...
This work defines strong equivalence across seven process features, assessable against human and machine cognition, and specifies design principles for GenAI that instantiate more process and preserve rather than erode human judgment and creativity.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
