Introduces Fragile benchmark showing LLMs have 28.6% average decision flip rate under fact-preserving framing and proposes Valign method to reduce flips via value-anchored hidden-state steering and projection.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Framing Matters: Addressing Framing Sensitivity in Decision-Making through Behaviorally-Grounded Value Alignment
Introduces Fragile benchmark showing LLMs have 28.6% average decision flip rate under fact-preserving framing and proposes Valign method to reduce flips via value-anchored hidden-state steering and projection.