Damiano Fornasiere
Supervisor
Titles as the sources gave them. In 2 entries, with 0 checked quotations.
In the Base
Every entry they appear in.
Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs
According to the excerpt, Davide Baldelli reports a MATS 10.0 study asking whether models can learn in context to control a score derived from their own activations, a test of whether probes that detect misbehaviour can be evaded. Across ten open-weight models, control is small and limited.
Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs
A preprint tests whether language models can control their own activations when shown a score derived from them, which would undermine probe-based misbehaviour detection. Across ten open-weight models, some move their scores but no more than a comparable writer model does.