Can You Trust Your Preference Models? Stackelberg Games for Alignment

arXiv:2610.00715v1 Announce Type: new Abstract: Preference-based alignment methods typically optimize against a single preference model, and can therefore be brittle when pairwise

arXiv:2603.22829v1 Announce Type: new Abstract: With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted

arXiv:2604.22167v1 Announce Type: cross Abstract: Language models are increasingly capable and are being rapidly deployed on a population-level scale. As a result, the safety of

arXiv:2604.05965v1 Announce Type: new Abstract: Transcending the single-preference paradigm, aligning LLMs with diverse human values is pivotal for robust deployment. Contemporary

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

arXiv:2603.22813v1 Announce Type: new Abstract: Humans often juggle multiple, sometimes conflicting objectives and shift their priorities as circumstances change, rather than

arXiv:2607.01715v1 Announce Type: new Abstract: Existing robust preference optimization for language-model alignment mainly studies pairwise supervision and places robustness at

arXiv:2604.00025v1 Announce Type: cross Abstract: Standard evaluation protocols reveal a counterintuitive phenomenon: on 7.7% of benchmark problems spanning five datasets, larger