A framework using statistical dissimilarity and LLM judges quantifies what fraction of the behavioral transition during fine-tuning is captured by each order parameter.
Emergent misalignment: Narrow finetuning can produce broadly misaligned LLMs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment
A framework using statistical dissimilarity and LLM judges quantifies what fraction of the behavioral transition during fine-tuning is captured by each order parameter.