2 papers 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.
A transition atlas of triples is constructed, where a residual-state feature and an MLP-update feature jointly predict a target residual feature, and validate candidate triples by ablating the decoded update feature.
The results demonstrate that suppressing entity-linked supervision during pretraining induces a shift in epistemic behavior: KLLMs rely less on parametric knowledge and more on external evidence, leading to improved reliability under realistic conditions, suggesting that pretraining-time control over knowledge acquisit...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
