A Roadmap to Impactful Pluralistic Alignment Research

arXiv:2608.24046v1 Announce Type: new Abstract: When an AI algorithm makes decisions that affect more than one person, aligning it becomes a problem of social choice: how should

arXiv:2604.23280v1 Announce Type: new Abstract: AI agents are now running real transactions, workflows, and sub-agent chains across organizational boundaries without continuous

arXiv:2605.08496v1 Announce Type: new Abstract: Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to

arXiv:2608.07642v1 Announce Type: new Abstract: Aligning large language models (LLMs) with human values remains a major challenge, especially for trustworthy AI. While existing

arXiv:2605.11496v1 Announce Type: new Abstract: Recent published evidence from frontier laboratories shows that contemporary AI models can recognise evaluation contexts, latently

arXiv:2603.18113v1 Announce Type: cross Abstract: As large language models (LLMs) increasingly shape content generation, interaction, and decision-making across the Web, aligning

arXiv:2609.05800v1 Announce Type: new Abstract: Activation steering controls LLM behavior at inference time by adding learned directions to hidden states, but existing methods

arXiv:2604.05274v1 Announce Type: new Abstract: Model alignment is currently applied in a vacuum, evaluated primarily through standardised benchmark performance. The purpose of