37 citations · 37 across the 2 of their papers we have counts for
2 papers
cs.LG2026
Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention
Matthew James Buchan
Activation steering can shift LLM behaviour, but standard evaluations do not typically test whether a sycophancy-reduction direction also suppresses agreement with factually correc…
cs.LG2022★ 37 cited
Accelerating Material Design with the Generative Toolkit for Scientific Discovery
Matteo Manica, Jannis Born, Joris Cadow +21
With the growing availability of data within various scientific domains, generative models hold enormous potential to accelerate scientific discovery. They harness powerful represe…