从静态个人价值观到情境化个性化：面向大语言模型的贝叶斯个性化价值对齐
From Static Personal Values to Contextualized Personalization: Bayesian Personalized Value Alignment for LLMs
浏览论文内容
中文总结 AI 辅助
针对大语言模型个性化价值对齐忽视情境差异的问题，提出贝叶斯推理时方法BaCVA，融合静态个人价值观与情境显著性，实现更准确、自适应的对齐并提升数据效率。
中文摘要 AI 辅助
随着大语言模型（LLMs）被期望适应多样化的用户偏好，个性化价值对齐变得越来越重要。然而，现有方法通常将模型输出与跨提示的静态价值档案对齐，忽视了价值维度的显著性在不同情境下会大幅变化。受勒温场论启发，该理论将人类行为视为个人倾向与情境约束共同作用的结果，我们将个人价值观建模为先验，将情境依赖的偏好建模为后验。我们提出BaCVA，一种推理时贝叶斯情境感知个性化价值对齐方法，通过整合静态个人价值观与情境特定的价值显著性来近似后验个性化偏好。BaCVA首先从一般规范性响应中估计情境价值显著性，然后采用双视角个性化模块，从互补的个人价值视角和情境驱动视角推断后验偏好。这种贝叶斯公式能够实现更准确、更自适应的个性化价值对齐，同时通过先验价值提高数据效率。在基准上的大量实验证明了其相对于强基线的优越性。
英文摘要
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 generally normative responses, and then employs a dual-view personalization module to infer posterior preferences from complementary personal-value and scenario-driven perspectives. This Bayesian formulation enables more accurate and adaptive personalized value alignment while improving data efficiency via prior values. Extensive experiments on benchmarks demonstrate its superiority over strong baselines.
发表机构
- Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）
- Microsoft Research Asia（微软亚洲研究院）
机构由 AI 辅助整理，请以论文原文为准。
