paper-with-me

Papers

BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment

2024-11-16 · Sizhe Wang, Yongqi Tong, Hengyuan Zhang, Dawei Li, Xin Zhang, Tianlong Chen

Reinforcement Learning with Human Feedback (RLHF) is the key to the success of large language models (LLMs) in recent years. In this work, we first introduce the concepts of knowledge breadth and knowledge depth, which measure the comprehensiveness and depth of an LLM or knowledge source respectively. We reveal that the imbalance in the number of prompts and responses can lead to a potential disparity in breadth and depth learning within alignment tuning datasets by showing that even a simple uniform method for balancing the number of instructions and responses can lead to significant improvements. Building on this, we further propose Balanced Preference Optimization (BPO), designed to dynamically augment the knowledge depth of each sample. BPO is motivated by the observation that the usefulness of knowledge varies across samples, necessitating tailored learning of knowledge depth. To achieve this, we introduce gradient-based clustering, estimating the knowledge informativeness and usefulness of each augmented sample based on the model's optimization direction. Our experimental results across various benchmarks demonstrate that BPO outperforms other baseline methods in alignment tuning while maintaining training efficiency. Furthermore, we conduct a detailed analysis of each component of BPO, providing guidelines for future research in preference data optimization.

📄 PDF Abstract BibTeX arXiv:2411.10914

Code (0)

등록된 구현이 없습니다.

Tasks

Informativeness

Similar Papers 제목 키워드 기반

Improving Safety Alignment via Balanced Direct Preference Optimization

2026-03-24 · Shiji Zhao, Mengyang Wang, Shukun Xiong, Fangzhou Chen 외 arxiv

With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. Reinforcement Learning from Human Feedback (RLHF) has been adopted …

Reinforcement Learning

AnnoDPO: Protein Functional Annotation Learning with Direct Preference Optimization

2025-06-08 · Zixuan Jiang, Renjing Xu

Deciphering protein function remains a fundamental challenge in protein representation learning. The task presents significant difficulties for protein language models (PLMs) due to the sheer volume of functional annotat…

Language ModelingLanguage ModellingLarge Language ModelProtein Function Prediction+1

$φ$-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models

2026-02-26 · Thanh-Dat Truong, Huu-Thien Tran, Jackson Cothren, Bhiksha Raj 외 arxiv

Fairness in Continual Learning for Large Multimodal Models (LMMs) is an emerging yet underexplored challenge, particularly in the presence of imbalanced data distributions that can lead to biased model updates and subopt…

Continual Learning

Looping in the Human Collaborative and Explainable Bayesian Optimization

2023-10-26 · Masaki Adachi, Brady Planden, David A. Howey, Michael A. Osborne 외

Like many optimizers, Bayesian optimization often falls short of gaining user trust due to opacity. While attempts have been made to develop human-centric optimizers, they typically assume user knowledge is well-specifie…

Bayesian Optimization

BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization

2024-06-30 · Gihun Lee, Minchan Jeong, Yujin Kim, Hojung Jung 외

While learning to align Large Language Models (LLMs) with human preferences has shown remarkable success, aligning these models to meet the diverse user preferences presents further challenges in preserving previous know…

Continual LearningGeneral KnowledgeKnowledge DistillationPersonalized and Emotional Conversation+1