Comparing two open LLMs, the paper claims that greater internal political feature richness predicts steerability and that refusals on benign prompts reflect capability deficits, but the causal evidence is missing.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth
Comparing two open LLMs, the paper claims that greater internal political feature richness predicts steerability and that refusals on benign prompts reflect capability deficits, but the causal evidence is missing.