Introduces tiered Moral Sensitivity Index for contextual bias and reports U-curve pattern where reasoning distillation reactivates bias circuits in LLMs.
Title resolution pending
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
-
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability
Introduces tiered Moral Sensitivity Index for contextual bias and reports U-curve pattern where reasoning distillation reactivates bias circuits in LLMs.