LATIDIA · Investigación

De los valores personales estáticos a la personalización contextualizada: alineación bayesiana de valores personalizados para LLM

arXiv: 2609.28942v1Tipo de anuncio: nuevo Resumen: La alineación de valores personalizada se ha vuelto cada vez más importante a medida que se espera que los modelos de lenguaje grandes (LLM) se adapten a las diversas preferencias del usuario. Sin embargo, el método existente

La noticia

arXiv:2609.28942v1 Announce Type: new Abstract: Personalized value alignment has become increasingly important as large language models (LLMs) are expected to accommodate diverse user preferences. However, existing methods typically align model outputs with a static value profile across prompts, overlooking that the salience of value dimensions varies substantially across contexts. Inspired by Lewin's Field Theory, which views human behavior as jointly shaped by personal dispositions and situational constraints, we model personal values as priors and context-dependent preferences as posteriors. We propose BaCVA, an inference-time Bayesian Context-aware personalized Value Alignment method that approximates posterior personalized preferences by integrating static personal values with scenario-specific value salience. BaCVA first estimates contextual value salience from