4 articles tagged with #social-choice-theory. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
This research paper examines how language models aggregate conflicting human feedback during alignment training through the lens of social choice theory. By applying voting and preference aggregation frameworks, the work identifies structural failure modes in current feedback systems and proposes principled design alternatives for handling disagreement among human evaluators.
A position paper argues that large language models should optimize for individual user preferences rather than aggregated 'average user' preferences, which masks critical information about preference diversity and values. The authors propose bounded personalization frameworks that balance individual autonomy with universal safety constraints, while addressing scalability and manipulation risks.
Researchers have developed a new preference learning framework that addresses bias in AI alignment by ensuring policies reflect true population distributions rather than just majority opinions. The approach uses social choice theory principles and has been validated on both recommendation tasks and large language model alignment.
A theoretical mathematics paper proves that strict majority voting rules cannot be completely described by any finite set of logical axioms, resolving a conjecture about the finite axiomatizability of measurable social decision frames. The research demonstrates that coherence violations in majority reasoning require arbitrarily long logical chains, meaning no bounded finite system can fully capture all properties of majority-based decision-making.
