paper-with-me

Papers

Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning

2025-02-20 · Huimin Xu, Xin Mao, Feng-Lin Li, Xiaobao Wu, Wang Chen, Wei zhang, Anh Tuan Luu

Direct Preference Optimization (DPO) often struggles with long-chain mathematical reasoning. Existing approaches, such as Step-DPO, typically improve this by focusing on the first erroneous step in the reasoning chain. However, they overlook all other steps and rely heavily on humans or GPT-4 to identify erroneous steps. To address these issues, we propose Full-Step-DPO, a novel DPO framework tailored for mathematical reasoning. Instead of optimizing only the first erroneous step, it leverages step-wise rewards from the entire reasoning chain. This is achieved by training a self-supervised process reward model, which automatically scores each step, providing rewards while avoiding reliance on external signals. Furthermore, we introduce a novel step-wise DPO loss, which dynamically updates gradients based on these step-wise rewards. This endows stronger reasoning capabilities to language models. Extensive evaluations on both in-domain and out-of-domain mathematical reasoning benchmarks across various base language models, demonstrate that Full-Step-DPO achieves superior performance compared to state-of-the-art baselines.

📄 PDF Abstract BibTeX arXiv:2502.14356

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical Reasoning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Self-training Language Models for Arithmetic Reasoning

2024-07-11 · Marek Kadlčík, Michal Štefánik

Recent language models achieve impressive results in tasks involving complex multistep reasoning, but scaling these capabilities further traditionally requires expensive collection of more annotated data. In this work, w…

Arithmetic Reasoning

S$^2$COPE: Self-Supervised Concept Discovery via Preference Learning

2026-06-12 · Shilong Xiang, Zirui Zhang, Chengzhi Mao arxiv

Current representation learning paradigms force a fundamental compromise: self-supervised methods scale to massive datasets but yield opaque features, whereas interpretable models remain bottlenecked by the need for dens…

Representation Learning

SSPO: Self-traced Step-wise Preference Optimization for Process Supervision and Reasoning Compression

2025-08-18 · Yuyang Xu, Yi Cheng, Haochao Ying, Zhuoyun Du 외 arxiv

Test-time scaling has proven effective in further enhancing the performance of pretrained Large Language Models (LLMs). However, mainstream post-training methods (i.e., reinforcement learning (RL) with chain-of-thought (…

Reinforcement Learning

SUDO: Enhancing Text-to-Image Diffusion Models with Self-Supervised Direct Preference Optimization

2025-04-20 · Liang Peng, Boxi Wu, Haoran Cheng, Yibo Zhao 외

Previous text-to-image diffusion models typically employ supervised fine-tuning (SFT) to enhance pre-trained base models. However, this approach primarily minimizes the loss of mean squared error (MSE) at the pixel level…

global-optimization

Prefer-DAS: Learning from Local Preferences and Sparse Prompts for Domain Adaptive Segmentation of Electron Microscopy

2026-02-23 · Jiabao Chen, Shan Xiong, Jialin Peng arxiv

Domain adaptive segmentation (DAS) is a promising paradigm for delineating intracellular structures from various large-scale electron microscopy (EM) without incurring extensive annotated data in each domain. However, th…

Unsupervised Domain AdaptationInteractive SegmentationContrastive Learning