Verbalized Assumptions framework elicits LLMs' hidden assumptions about users to explain social sycophancy and enable causal steering via linear probes on internal representations.
mental_model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Verbalizing LLMs' assumptions to explain and control sycophancy
Verbalized Assumptions framework elicits LLMs' hidden assumptions about users to explain social sycophancy and enable causal steering via linear probes on internal representations.