EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference M

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

arXiv:2604.26120v1 Announce Type: new Abstract: Behavioral logs provide rich signals for user modeling, but are noisy and interleaved across diverse intents. Recent work uses LLMs

arXiv:2610.00061v1 Announce Type: new Abstract: Personalizing large language models (LLMs) requires aligning generation behavior with user-specific preferences rather than

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

arXiv:2610.02568v1 Announce Type: new Abstract: Personal advice, including relationship advice, now ranks among the most common uses of generative AI. But language models (LMs)

arXiv:2603.23231v1 Announce Type: new Abstract: Empowering large language models with long-term memory is crucial for building agents that adapt to users' evolving needs. However,

arXiv:2607.13162v2 Announce Type: cross Abstract: What a language model will and will not do is largely set during post-training, but which behaviors it expresses, hides, or