Pareto-Guided Teacher Alignment for Fair Personalized Text Generation

• URL: http://arxiv.org/abs/2606.10126v1
• Date: Mon, 08 Jun 2026 19:57:13 GMT
• Title: Pareto-Guided Teacher Alignment for Fair Personalized Text Generation
• Abstract summary: We study fairness mitigation in personalized generation as a constrained multi-objective alignment problem.<n>Our results show that fairness mitigation effects are objective-dependent and transfer inconsistently across domains and model families.
• Score: 8.06425428468097
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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. 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. 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. 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. 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.

Related papers

• CHOIR: Collaborative Harmonization fOr Inference Robustness [25.458744810976672]
  Persona-assigned Large Language Models (LLMs) can adopt diverse roles, enabling personalized and context-aware reasoning.<n>Minor demographic perturbations in personas, such as simple pronoun changes, can alter reasoning trajectories, leading to divergent sets of correct answers.<n>We propose CHOIR, a test-time framework that harmonizes multiple persona-conditioned reasoning signals into a unified prediction.
  arXiv  Detail & Related papers  (2025-10-26T01:20:24Z)
• Strategic Costs of Perceived Bias in Fair Selection [25.24305795734348]
  Meritocratic systems aim to impartially reward skill and effort.<n> persistent disparities across race, gender, and class challenge this ideal.<n>We develop a game-theoretic model in which candidates from different socioeconomic groups differ in perceived post-selection value.
  arXiv  Detail & Related papers  (2025-10-23T14:38:05Z)
• SONA: Learning Conditional, Unconditional, and Mismatching-Aware Discriminator [54.562217603802075]
  We introduce Sum of Naturalness and Alignment (SONA), which employs separate projections for naturalness (authenticity) and alignment in the final layer with an inductive bias.<n>Experiments on class-conditional generation tasks show thatSONA achieves superior sample quality and conditional alignment compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-10-06T08:26:06Z)
• DisCo: Reinforcement with Diversity Constraints for Multi-Human Generation [60.741022906593685]
  DisCo is the first RL-based framework to directly optimize identity diversity in multi-human generation.<n>DisCo fine-tunes flow-matching models via Group-Relative Policy Optimization.<n>On the DiverseHumans Testset, DisCo achieves 98.6 Unique Face Accuracy and near-perfect Global Identity Spread.
  arXiv  Detail & Related papers  (2025-10-01T19:28:51Z)
• APFEx: Adaptive Pareto Front Explorer for Intersectional Fairness [16.993547305381327]
  We introduce APFEx, the first framework to explicitly model intersectional fairness as a joint optimization problem.<n>APFEx combines adaptive multi-objectives, gradient weighting, and exploration strategies to navigate fairness-accuracy trade-offs.<n>Experiments on four real-world datasets demonstrate APFEx's superiority, reducing fairness violations while maintaining competitive accuracy.
  arXiv  Detail & Related papers  (2025-09-17T11:13:22Z)
• Fairness-Aware Meta-Learning via Nash Bargaining [63.44846095241147]
  We introduce a two-stage meta-learning framework to address issues of group-level fairness in machine learning. The first stage involves the use of a Nash Bargaining Solution (NBS) to resolve hypergradient conflicts and steer the model. We show empirical effects across various fairness objectives in six key fairness datasets and two image classification tasks.
  arXiv  Detail & Related papers  (2024-06-11T07:34:15Z)
• Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment [103.12563033438715]
  Alignment in artificial intelligence pursues consistency between model responses and human preferences as well as values. Existing alignment techniques are mostly unidirectional, leading to suboptimal trade-offs and poor flexibility over various objectives. We introduce controllable preference optimization (CPO), which explicitly specifies preference scores for different objectives.
  arXiv  Detail & Related papers  (2024-02-29T12:12:30Z)
• Mitigating Group Bias in Federated Learning for Heterogeneous Devices [1.181206257787103]
  Federated Learning is emerging as a privacy-preserving model training approach in distributed edge applications. Our work proposes a group-fair FL framework that minimizes group-bias while preserving privacy and without resource utilization overhead.
  arXiv  Detail & Related papers  (2023-09-13T16:53:48Z)
• DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervision [73.80009454050858]
  This work presents a self-supervised model, called DualFair, that can debias sensitive attributes like gender and race from learned representations. Our model jointly optimize for two fairness criteria - group fairness and counterfactual fairness.
  arXiv  Detail & Related papers  (2023-03-15T07:13:54Z)
• Mitigating Face Recognition Bias via Group Adaptive Classifier [53.15616844833305]
  This work aims to learn a fair face representation, where faces of every group could be more equally represented. Our work is able to mitigate face recognition bias across demographic groups while maintaining the competitive accuracy.
  arXiv  Detail & Related papers  (2020-06-13T06:43:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.