Debiasing Online Preference Learning via Preference Feature Preservation

• URL: http://arxiv.org/abs/2506.11098v1
• Date: Fri, 06 Jun 2025 13:19:07 GMT
• Title: Debiasing Online Preference Learning via Preference Feature Preservation
• Authors: Dongyoung Kim, Jinsung Yoon, Jinwoo Shin, Jaehyung Kim,
• Abstract summary: Recent preference learning frameworks simplify human preferences with binary pairwise comparisons and scalar rewards.<n>This could make large language models' responses biased to mostly preferred features, and would be exacerbated during the iterations of online preference learning steps.<n>We propose Preference Feature Preservation to maintain the distribution of human preference features and utilize such rich signals throughout the online preference learning process.
• Score: 64.55924745257951
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent preference learning frameworks for large language models (LLMs) simplify human preferences with binary pairwise comparisons and scalar rewards. This simplification could make LLMs' responses biased to mostly preferred features, and would be exacerbated during the iterations of online preference learning steps. To address these challenges, we propose a novel framework coined PFP (Preference Feature Preservation). The key idea of PFP is maintaining the distribution of human preference features and utilizing such rich signals throughout the online preference learning process. Specifically, PFP first extract preference features from offline pairwise human preference data and trains a feature classifier. Then, using trained classifier and the distribution preserving optimization, PFP maps appropriate preference features for a new input instruction during online learning. Lastly, PFP trains LLM using the existing preference learning method, by incorporating the preference feature into system prompts and enabling LLM to explicitly handle various human preferences. Our experiments demonstrate that PFP successfully mitigates the bias in preference features during online learning, and hence achieves superior performance compared to previous preference learning methods on standard benchmarks to evaluate LLM alignment.

Related papers

• PITA: Preference-Guided Inference-Time Alignment for LLM Post-Training [9.093854840532062]
  PITA is a novel framework that integrates preference feedback directly into the LLM's token generation.<n> PITA learns a small preference-based guidance policy to modify token probabilities at inference time without fine-tuning.<n>We evaluate PITA across diverse tasks, including mathematical reasoning and sentiment classification.
  arXiv  Detail & Related papers  (2025-07-26T21:46:32Z)
• Intuitionistic Fuzzy Sets for Large Language Model Data Annotation: A Novel Approach to Side-by-Side Preference Labeling [0.0]
  This paper introduces a novel framework based on intuitionistic fuzzy sets (IFS) for modeling and aggregating human preferences in large language models (LLMs)<n>Our approach captures not only the degree of preference but also the uncertainty and hesitation inherent in human judgment through membership, non-membership, and hesitation degrees.<n> Experimental validation on multiple datasets demonstrates that our IFS-based approach significantly improves annotation consistency, reduces annotator fatigue, and produces higher-quality preference data.
  arXiv  Detail & Related papers  (2025-05-30T04:20:00Z)
• Multi-Type Preference Learning: Empowering Preference-Based Reinforcement Learning with Equal Preferences [12.775486996512434]
  Preference-Based reinforcement learning learns directly from the preferences of human teachers regarding agent behaviors. Existing PBRL methods often learn from explicit preferences, neglecting the possibility that teachers may choose equal preferences. We propose a novel PBRL method, Multi-Type Preference Learning (MTPL), which allows simultaneous learning from equal preferences while leveraging existing methods for learning from explicit preferences.
  arXiv  Detail & Related papers  (2024-09-11T13:43:49Z)
• Pareto-Optimal Learning from Preferences with Hidden Context [17.590330740964266]
  We propose POPL, which enables pluralistic alignment by framing discrepant group preferences as objectives with potential trade-offs.<n>Our theoretical and empirical evaluations demonstrate that POPL surpasses baseline methods in learning sets of reward functions and policies.<n>We illustrate that POPL can also serve as a foundation for techniques optimizing specific notions of group fairness.
  arXiv  Detail & Related papers  (2024-06-21T18:57:38Z)
• Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment [72.99676237703099]
  We propose a new framework that boosts the alignment of large language models with human preferences.<n>Our key idea is leveraging the human prior knowledge within the small (seed) data.<n>We introduce a noise-aware preference learning algorithm to mitigate the risk of low quality within generated preference data.
  arXiv  Detail & Related papers  (2024-06-06T18:01:02Z)
• Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment [104.18002641195442]
  We introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data. Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation.
  arXiv  Detail & Related papers  (2024-05-31T14:21:04Z)
• Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization [105.3612692153615]
  We propose a new axis based on eliciting preferences jointly over instruction-response pairs.<n>Joint preferences over instruction and response pairs can significantly enhance the alignment of large language models.
  arXiv  Detail & Related papers  (2024-03-31T02:05:40Z)
• Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts [95.09994361995389]
  Relative Preference Optimization (RPO) is designed to discern between more and less preferred responses derived from both identical and related prompts. RPO has demonstrated a superior ability to align large language models with user preferences and to improve their adaptability during the training process.
  arXiv  Detail & Related papers  (2024-02-12T22:47:57Z)
• Nash Learning from Human Feedback [86.09617990412941]
  We introduce an alternative pipeline for the fine-tuning of large language models using pairwise human feedback. We term this approach Nash learning from human feedback (NLHF) We present a novel algorithmic solution, Nash-MD, founded on the principles of mirror descent.
  arXiv  Detail & Related papers  (2023-12-01T19:26:23Z)

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.