We have 5 of 34 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.
There is not enough public evidence for us to confidently state that midtraining can address the core difficulties inherent in aligning powerful AI systems, and it is believed that demonstrations must be present either in midtraining or post-training datasets for these rules to be robustly learned.
Results show that inoculation with a learned association introduced via midtraining can shape selective generalisation, and more work is needed before this approach can become a load-bearing component in a developer's safety framework.
Overall, it is shown IRT is a ready-made toolkit for reading, reducing, and auditing safety benchmarks, which frontier labs and evaluators adopt.
The Activation Controllability Benchmark is introduced to quantify the extent to which models can modulate their residual stream via natural-language instruction, and suggests that control over the activation space itself could become a confound for monitoring as introspective capabilities increase.
An unsupervised psychometric pipeline is introduced that recovers four interpretable behavioural factors from model rollouts that can be considered in terms of learning, scaling, and composing traits in weight space, providing a bridge between personality measurement, model editing, and safety.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
