Safety
AI Alignment From Social Choice Perspectives
arXiv:2606.21550v2 Announce Type: replace Abstract: Alignment from human feedback uses human judgments about model outputs to steer the behavior of language models after pretraining. When those judgme
arXiv:2606.21550v2 Announce Type: replace Abstract: Alignment from human feedback uses human judgments about model outputs to steer the behavior of language models after pretraining. When those judgments reflect conflicting views of desirable behavior, the learned objective becomes an aggregate determination of what the model should prefer. We survey recent work that has studied this aggregation problem through the lens of social choice theory. We illustrate how the social choice perspective helps identify failure modes in the feedback aggregation layer and reveals a broader design space for handling disagreement in explicit and principled ways.
Related
- PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization
- VISPA: Pluralistic Alignment via Automatic Value Selection and Activation
- Societal Alignment Frameworks Can Improve LLM Alignment
- Culturally Grounded Personas in Large Language Models: Characterization and Alignment with Socio-Psychological Value Frameworks
Source: arXiv cs.AI | 2026-10-16