Recursive generative retraining with heterogeneous rewards converges to a stable distribution satisfying a weighted Nash bargaining solution, preserving diversity under stated conditions.
arXiv preprint arXiv:2411.04991 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3verdicts
UNVERDICTED 3representative citing papers
Develops self-consistency monitoring for preference annotators and derives sample-complexity bounds showing linear contracts achieve near-ideal performance faster than binary ones under continuous actions.
Position paper advocating personalized preference learning in LLMs over aggregated approaches, grounded in social choice theory and demographic variation.
citing papers explorer
-
Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
Recursive generative retraining with heterogeneous rewards converges to a stable distribution satisfying a weighted Nash bargaining solution, preserving diversity under stated conditions.
-
How Humans Help LLMs: Assessing and Incentivizing Human Preference Annotators
Develops self-consistency monitoring for preference annotators and derives sample-complexity bounds showing linear contracts achieve near-ideal performance faster than binary ones under continuous actions.
-
Large Language Models Should Learn Personalized Rather Than Aggregated Human Preferences
Position paper advocating personalized preference learning in LLMs over aggregated approaches, grounded in social choice theory and demographic variation.