Semantic Reward Collapse compresses different epistemic issues into unified rewards in preference optimization, risking loss of calibrated uncertainty, with Constitutional Reward Stratification proposed as a domain-stratified alternative framework.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Semantic Reward Collapse and the Preservation of Epistemic Integrity in Adaptive AI Systems
Semantic Reward Collapse compresses different epistemic issues into unified rewards in preference optimization, risking loss of calibrated uncertainty, with Constitutional Reward Stratification proposed as a domain-stratified alternative framework.