Pareto-Guided Teacher Alignment for Fair Personalized Text Generation

基于帕累托引导教师对齐的公平个性化文本生成

Personalized persuasive text generation can improve relevance and engagement, but demographic conditioning may also introduce unequal framing across groups. We study fairness mitigation in personalized generation as a constrained multi-objective alignment problem: reduce demographic disparities while preserving personalization fidelity.

个性化说服性文本生成可以提高相关性和参与度，但基于人口统计学特征的条件化也可能在不同群体间引入不平等的框架。我们将个性化生成中的公平性缓解研究视为一个受约束的多目标对齐问题：即在保持个性化保真度的同时，减少人口统计学差异。

We propose a Pareto-guided teacher alignment framework that combines revision-based candidate generation, pair-aware feasibility gating, Pareto-style candidate selection, and optional preference optimization through supervised fine-tuning and direct preference optimization.

我们提出了一种帕累托引导的教师对齐框架，该框架结合了基于修订的候选生成、成对感知可行性门控、帕累托风格的候选选择，以及通过监督微调和直接偏好优化（DPO）进行的可选偏好优化。

We evaluate the framework on climate change and vaccination persuasion tasks using a controlled context-rich demographic grid with matched gender and age pairs and a unified five-audit evaluation suite spanning persuasion bias, formality disparity, emotional framing disparity, lexical association disparity, and personalization fidelity.

我们在气候变化和疫苗接种说服任务上评估了该框架，使用了包含匹配性别和年龄对的受控、上下文丰富的人口统计网格，以及一套统一的五维审计评估套件，涵盖了说服偏见、正式程度差异、情感框架差异、词汇关联差异和个性化保真度。

Across both domains and cross-family transfer settings, no single alignment strategy dominates all objectives simultaneously. Instead, methods occupy different regions of a fairness-personalization Pareto frontier: some achieve stronger disparity reductions, while others better preserve personalization or demographic stability.

在两个领域和跨模型家族的迁移设置中，没有任何单一的对齐策略能同时主导所有目标。相反，各种方法占据了公平性-个性化帕累托前沿的不同区域：一些方法实现了更强的差异缩减，而另一些方法则更好地保持了个性化或人口统计学的稳定性。

Our results show that fairness mitigation effects are objective-dependent and transfer inconsistently across domains and model families, motivating bounded-regression, multi-audit model selection over single-metric optimization for fairness-sensitive personalized generation.

我们的研究结果表明，公平性缓解效果取决于具体目标，且在不同领域和模型家族间的迁移表现不一致。这促使我们在进行公平敏感的个性化生成时，应采用有界回归和多重审计的模型选择，而非单一指标的优化。