paper-with-me

홈 › Papers

PMoL: Parameter Efficient MoE for Preference Mixing of LLM Alignment

2024-11-02 · Dongxu Liu, Bing Xu, Yinzhuo Chen, Bufan Xu, Wenpeng Lu, Muyun Yang, Tiejun Zhao

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 struggles with handling multiple competing preferences. This leads to a decrease in the alignment of LLMs with human preferences. To address this issue, we propose Preference Mixture of LoRAs (PMoL) from the perspective of model architecture, which can adapt to any number of preferences to mix. PMoL combines Mixture of Experts (MoE) and Low Rank Adaptor (LoRA). This architecture is innovatively applied to the research of preference alignment and has achieved significant performance improvement. The expert group soft loss is used to enable MoE with the ability to mix preferences. Through comprehensive evaluation by the reward model and GPT-4o, the experiment results show that PMoL has superior preference mixing capabilities compared to baseline methods. PMoL achieves better preference alignment with lower training costs.

📄 PDF Abstract BibTeX arXiv:2411.01245

Code (0)

등록된 구현이 없습니다.

Tasks

Mixture-of-Experts

Methods 이 논문이 사용한 방법론

MoE 설명 없음

Similar Papers 제목 키워드 기반

DeepMol: An Automated Machine and Deep Learning Framework for Computational Chemistr

2024-06-01 · bioRxiv 2024 6 · João Correia, João Capela, Miguel Rocha

The domain of computational chemistry has experienced a significant evolution due to the introduction of Machine Learning (ML) technologies. Despite its potential to revolutionize the field, researchers are often encumbe…

Activity PredictionAutoMLComputational chemistryDeep Learning+2

DeepMoLM: Leveraging Visual and Geometric Structural Information for Molecule-Text Modeling

2026-01-21 · Jing Lan, Hexiao Ding, Hongzhao Chen, Yufeng Jiang 외 arxiv

AI models for drug discovery and chemical literature mining must interpret molecular images and generate outputs consistent with 3D geometry and stereochemistry. Most molecular language models rely on strings or graphs, …

Drug Discovery

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

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

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 approac…

Diversityreinforcement-learningReinforcement Learning

Balancing Privacy, Utility, and Safety in LLM Alignment through Preference Optimization

2026-08-31 · Dishu Yang, Jingjing Liu, Jize Li arxiv

Preference optimization is widely used to align large language models with human preferences, but preference-data composition may also influence privacy-relevant memorization. We examine whether adding synthetic privacy-…

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