ShaPO improves LLM safety robustness over standard preference optimization by enforcing worst-case objectives via selective geometry control at token and reward levels.
To simplify the pipeline, Direct Preference Optimization (DPO) (Rafailov et al.,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control
ShaPO improves LLM safety robustness over standard preference optimization by enforcing worst-case objectives via selective geometry control at token and reward levels.