paper-with-me

홈 › Papers

sDPO: Don't Use Your Data All at Once

2024-03-28 · Dahyun Kim, Yungi Kim, Wonho Song, Hyeonwoo Kim, Yunsu Kim, Sanghoon Kim, Chanjun Park

As development of large language models (LLM) progresses, aligning them with human preferences has become increasingly important. We propose stepwise DPO (sDPO), an extension of the recently popularized direct preference optimization (DPO) for alignment tuning. This approach involves dividing the available preference datasets and utilizing them in a stepwise manner, rather than employing it all at once. We demonstrate that this method facilitates the use of more precisely aligned reference models within the DPO training framework. Furthermore, sDPO trains the final model to be more performant, even outperforming other popular LLMs with more parameters.

📄 PDF Abstract BibTeX arXiv:2403.19270

Code (0)

등록된 구현이 없습니다.

Tasks

All

Methods 이 논문이 사용한 방법론

DPO 설명 없음

Similar Papers 제목 키워드 기반

Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning

2026-05-26 · Zehao Liu, Yuanpu Cao, Jinghui Chen, Vasant G. Honavar arxiv

Self-Distillation Policy Optimization (SDPO) provides dense token-level credit assignment for reinforcement learning with large language models by leveraging the model's own feedback-conditioned predictions as a self-tea…

Reinforcement Learning

Aligning Few-Step Diffusion Models with Dense Reward Difference Learning

2024-11-18 · Ziyi Zhang, Li Shen, Sen Zhang, Deheng Ye 외

Aligning diffusion models with downstream objectives is essential for their practical applications. However, standard alignment methods often struggle with step generalization when directly applied to few-step diffusion …

Denoising

SDPO: Segment-Level Direct Preference Optimization for Social Agents

2025-01-03 · Aobo Kong, Wentao Ma, Shiwan Zhao, Yongbin Li 외

Social agents powered by large language models (LLMs) can simulate human social behaviors but fall short in handling complex goal-oriented social dialogues. Direct Preference Optimization (DPO) has proven effective in al…

Reinforcement Learning via Self-Distillation

2026-01-28 · Jonas Hübotter, Frederike Lübeck, Lejs Behric, Anton Baumann 외 arxiv

Large language models are increasingly post-trained with reinforcement learning in verifiable domains such as code and math. Yet, current methods for reinforcement learning with verifiable rewards (RLVR) learn only from …

Reinforcement Learning

Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks

2018-01-29 · CVPR 2018 6 · Jason Kuen, Xiangfei Kong, Zhe Lin, Gang Wang 외

It is desirable to train convolutional networks (CNNs) to run more efficiently during inference. In many cases however, the computational budget that the system has for inference cannot be known beforehand during trainin…

image-classificationImage ClassificationObject Recognition