Recursive generative retraining with pluralistic preferences converges to a stable diverse distribution that satisfies a weighted Nash bargaining solution.
Representative social choice: From learning theory to ai alignment.arXiv preprint arXiv:2410.23953
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Models consensus as a PAC-learnable interval in embedded 1D opinion space via ERM that maximizes expected agreement over an issue distribution.
citing papers explorer
-
Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
Recursive generative retraining with pluralistic preferences converges to a stable diverse distribution that satisfies a weighted Nash bargaining solution.
-
Probably Approximately Consensus: On the Learning Theory of Finding Common Ground
Models consensus as a PAC-learnable interval in embedded 1D opinion space via ERM that maximizes expected agreement over an issue distribution.