paper-with-me

홈 › Papers

MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment

2025-02-25 · Tianze Wang, Dongnan Gui, Yifan Hu, Shuhang Lin, Linjun Zhang

Reinforcement Learning from Human Feedback (RLHF) has shown promise in aligning large language models (LLMs). Yet its reliance on a singular reward model often overlooks the diversity of human preferences. Recent approaches address this limitation by leveraging multi-dimensional feedback to fine-tune corresponding reward models and train LLMs using reinforcement learning. However, the process is costly and unstable, especially given the competing and heterogeneous nature of human preferences. In this paper, we propose Mixing Preference Optimization (MPO), a post-processing framework for aggregating single-objective policies as an alternative to both multi-objective RLHF (MORLHF) and MaxMin-RLHF. MPO avoids alignment from scratch. Instead, it log-linearly combines existing policies into a unified one with the weight of each policy computed via a batch stochastic mirror descent. Empirical results demonstrate that MPO achieves balanced performance across diverse preferences, outperforming or matching existing models with significantly reduced computational costs.

📄 PDF Abstract BibTeX arXiv:2502.18699

Code (0)

등록된 구현이 없습니다.

Tasks

Diversityreinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

PMoL: Parameter Efficient MoE for Preference Mixing of LLM Alignment

2024-11-02 · Dongxu Liu, Bing Xu, Yinzhuo Chen, Bufan Xu 외

Reinforcement Learning from Human Feedback (RLHF) has been proven to be an effective method for preference alignment of large language models (LLMs) and is widely used in the post-training process of LLMs. However, RLHF …

Mixture-of-Experts

Privacy Amplification by Mixing and Diffusion Mechanisms

2019-05-29 · NeurIPS 2019 12 · Borja Balle, Gilles Barthe, Marco Gaboardi, Joseph Geumlek

A fundamental result in differential privacy states that the privacy guarantees of a mechanism are preserved by any post-processing of its output. In this paper we investigate under what conditions stochastic post-proces…

SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning

2025-05-05 · Tianjian Li, Daniel Khashabi

Aligning language models with human preferences relies on pairwise preference datasets. While some studies suggest that on-policy data consistently outperforms off -policy data for preference learning, others indicate th…

Language ModelingLanguage ModellingMath

A Dirichlet Process Mixture Model of Discrete Choice

2018-01-19 · Rico Krueger, Akshay Vij, Taha H. Rashidi

We present a mixed multinomial logit (MNL) model, which leverages the truncated stick-breaking process representation of the Dirichlet process as a flexible nonparametric mixing distribution. The proposed model is a Diri…

model

HP-Edit: A Human-Preference Post-Training Framework for Image Editing

2026-04-21 · Fan Li, Chonghuinan Wang, Lina Lei, Yuping Qiu 외 arxiv

Common image editing tasks typically adopt powerful generative diffusion models as the leading paradigm for real-world content editing. Meanwhile, although reinforcement learning (RL) methods such as Diffusion-DPO and Fl…

Reinforcement LearningImage Editing