We have 4 of 5 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.
Instruction-following language models can comply with requests that conflict with intended behaviors and safety alignment. We introduce a training-free weight-editing approach for reducing compliance with targeted undesirable instructions. Our method needs only forward passes on a small set of prompt pairs per target b...
It is proved that the overlap between a target and other concepts lower-bounds the damage any robust erasure must inflict on them, with the trade-off scaling linearly in the degree of overlap.
This paper reveals a significant shortcoming in class unlearning evaluations: overlooking the underlying class geometry can cause information leakage about the forgotten class, and proposes a new fine-tuning objective that mitigates this privacy leakage by approximating the distribution over the remaining classes that...
This work presents the first systematic evaluation framework for agentic abstention, and identifies failure modes such as post-hoc abstention, in which agents execute irreversible actions before recognizing abstention triggers.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
