mlsanityData to 7 Oct 2026

FairPO: Robust Preference Optimization for Fair Multi-Label Learning

arXiv 2505.02433 ↗First posted 5 May 2025cs.LG cs.AIcited by 0

On the map: LLM alignment / RLHF / preference optimisation → LLM preference optimization methods

Abstract (arXiv)

Multi-label classification (MLC) often suffers from performance disparities across labels. We propose FairPO, a framework combining preference-based loss and group-robust optimization to improve fairness by targeting underperforming labels. FairPO partitions labels into a textitprivileged set for targeted improvement and a textitnon-privileged set to maintain baseline performance. For privileged labels, a DPO-inspired preference loss addresses hard examples by correcting ranking errors between true labels and their confusing counterparts. A constrained objective maintains performance for non-privileged labels, while a Group Robust Preference Optimization (GRPO) formulation adaptively balances both objectives to mitigate bias. We also demonstrate FairPO's versatility with reference-free variants using Contrastive (CPO) and Simple (SimPO) Preference Optimization.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 27 of its 55 references that are in the map. First posted on arXiv 5 May 2025.

Builds on

27 of 55 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024SimPO: Simple Preference Optimization with a Reference-Free Reward23 May
  2. 2024Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study16 Apr
  3. 2024Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation16 Jan
  4. 2022Training language models to follow instructions with human feedback4 Mar

Other references · 23

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  5. 2017Deep reinforcement learning from human preferencescited by 3,846
  6. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  7. 2023Mistral 7Bcited by 3,065
  8. 2020Learning to summarize from human feedbackcited by 2,562
  9. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  10. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  11. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  12. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
11 more
  1. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 671
  2. 2017CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learningcited by 459
  3. 2020Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamicscited by 423
  4. 2020Identifying Mislabeled Data using the Area Under the Margin Rankingcited by 259
  5. 2016CNN-RNN: A Unified Framework for Multi-label Image Classificationcited by 189
  6. 2019IPO: Interior-point Policy Optimization under Constraintscited by 119
  7. 2024Group Robust Preference Optimization in Reward-free RLHFcited by 94
  8. 2014CNN: Single-label to Multi-labelcited by 62
  9. 2018The Impact of Class Rebalancing Techniques on the Performance and Interpretation of Defect Prediction Modelscited by 29
  10. 2023SimFair: A Unified Framework for Fairness-Aware Multi-Label Classificationcited by 7
  11. 2025Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental Learningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization
  2. 2026Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization
  3. 2024Geometric-Averaged Preference Optimization for Soft Preference Labels
  4. 2026Distributionally Robust Listwise Preference Optimization
  5. 2024Multi-Preference Optimization: Generalizing DPO via Set-Level Contrasts
  6. 2026Calibrated Preference Learning: The Case of Label Ranking
  7. 2024Configurable Fairness: Direct Optimization of Parity Metrics via Vision-Language Models
  8. 2025Listwise Direct Preference Optimization with Multi-Dimensional Preference Mixing