Pareto-Optimal Learning from Preferences with Hidden Context

• URL: http://arxiv.org/abs/2406.15599v2
• Date: Fri, 07 Feb 2025 17:29:48 GMT
• Title: Pareto-Optimal Learning from Preferences with Hidden Context
• Authors: Ryan Bahlous-Boldi, Li Ding, Lee Spector, Scott Niekum,
• Abstract summary: We propose POPL, which enables pluralistic alignment by framing discrepant group preferences as objectives with potential trade-offs. Our theoretical and empirical evaluations demonstrate that POPL surpasses baseline methods in learning sets of reward functions and policies. We illustrate that POPL can also serve as a foundation for techniques optimizing specific notions of group fairness.
• Score: 17.590330740964266
• License:
• Abstract: Ensuring AI models align with human values is essential for their safety and functionality. Reinforcement learning from human feedback (RLHF) leverages human preferences to achieve this alignment. However, when preferences are sourced from diverse populations, point estimates of reward can result in suboptimal performance or be unfair to specific groups. We propose Pareto Optimal Preference Learning (POPL), which enables pluralistic alignment by framing discrepant group preferences as objectives with potential trade-offs, aiming for policies that are Pareto-optimal on the preference dataset. POPL utilizes lexicase selection, an iterative process that selects diverse and Pareto-optimal solutions. Our theoretical and empirical evaluations demonstrate that POPL surpasses baseline methods in learning sets of reward functions and policies, effectively catering to distinct groups without access to group numbers or membership labels. We verify the performance of POPL on a stateless preference learning setting, a Minigrid RL domain, Metaworld robotics benchmarks, as well as large language model (LLM) fine-tuning. We illustrate that POPL can also serve as a foundation for techniques optimizing specific notions of group fairness, ensuring safe and equitable AI model alignment.

Related papers

• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications. Ensuring their alignment with the diverse preferences of individual users has become a critical challenge. We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness [27.43137305486112]
  We propose a novel Self-supervised Preference Optimization (SPO) framework, which constructs a self-supervised preference degree loss combined with the alignment loss. The results demonstrate that SPO can be seamlessly integrated with existing preference optimization methods to achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-09-26T12:37:26Z)
• Adaptive Preference Scaling for Reinforcement Learning with Human Feedback [103.36048042664768]
  Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values. We propose a novel adaptive preference loss, underpinned by distributionally robust optimization (DRO) Our method is versatile and can be readily adapted to various preference optimization frameworks.
  arXiv  Detail & Related papers  (2024-06-04T20:33:22Z)
• Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data [102.16105233826917]
  Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and contrastive learning.
  arXiv  Detail & Related papers  (2024-04-22T17:20:18Z)
• 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. 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)
• MaxMin-RLHF: Alignment with Diverse Human Preferences [101.57443597426374]
  Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data. We learn a mixture of preference distributions via an expectation-maximization algorithm to better represent diverse human preferences. Our algorithm achieves an average improvement of more than 16% in win-rates over conventional RLHF algorithms.
  arXiv  Detail & Related papers  (2024-02-14T03:56:27Z)
• 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)
• Group Preference Optimization: Few-Shot Alignment of Large Language Models [28.464834028110538]
  Group Preference Optimization steers language models to preferences of individual groups in a few-shot manner. We empirically validate the efficacy of GPO through rigorous evaluations using large language models with varied sizes. Our results demonstrate that GPO not only aligns models more accurately but also requires fewer group-specific preferences, and less training and inference computing resources.
  arXiv  Detail & Related papers  (2023-10-17T18:41:57Z)

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.