An explicitly exploratory iterative NLHF method achieves O(sqrt(T)) regret for Nash equilibria under general preference models, removing the exponential KL dependence that plagues standard iterative approaches.
Jackpot! alignment as a maximal lottery
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
The angular mean of voter scoring vectors satisfies long-run individual proportionality for sequential linear ranking decisions.
Context-ordinal Nash equilibria are defined via social choice aggregation of ordinal preferences, shown to exist under mild conditions, with regularization, approximation, regret notions, complexity results, and learning rules developed.
The authors propose a conceptual framework integrating stakeholder-LLM alignment methods, social choice-based aggregation for collective decisions, and stakeholder-centric evaluations to achieve fair multi-agent personalization.
This survey examines applications of social choice theory to aggregating human feedback in AI alignment, identifying failure modes and expanding design options for disagreement.
citing papers explorer
-
Efficient Exploration for Iterative Nash Preference Optimization
An explicitly exploratory iterative NLHF method achieves O(sqrt(T)) regret for Nash equilibria under general preference models, removing the exponential KL dependence that plagues standard iterative approaches.
-
The End Justifies the Mean: A Linear Ranking Rule for Proportional Sequential Decisions
The angular mean of voter scoring vectors satisfies long-run individual proportionality for sequential linear ranking decisions.
-
Nash without Numbers: A Social Choice Approach to Mixed Equilibria in Context-Ordinal Games
Context-ordinal Nash equilibria are defined via social choice aggregation of ordinal preferences, shown to exist under mild conditions, with regularization, approximation, regret notions, complexity results, and learning rules developed.
-
Fair Agents: Balancing Multistakeholder Alignment in Multi-Agent Personalization Systems
The authors propose a conceptual framework integrating stakeholder-LLM alignment methods, social choice-based aggregation for collective decisions, and stakeholder-centric evaluations to achieve fair multi-agent personalization.
-
AI Alignment From Social Choice Perspectives
This survey examines applications of social choice theory to aggregating human feedback in AI alignment, identifying failure modes and expanding design options for disagreement.