paper-with-me

Papers

Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback

2025-01-18 · Yen-Ting Lin, Di Jin, Tengyu Xu, Tianhao Wu, Sainbayar Sukhbaatar, Chen Zhu, Yun He, Yun-Nung Chen, Jason Weston, Yuandong Tian, Arash Rahnama, Sinong Wang, Hao Ma, Han Fang

Large language models (LLMs) have recently demonstrated remarkable success in mathematical reasoning. Despite progress in methods like chain-of-thought prompting and self-consistency sampling, these advances often focus on final correctness without ensuring that the underlying reasoning process is coherent and reliable. This paper introduces Step-KTO, a training framework that combines process-level and outcome-level binary feedback to guide LLMs toward more trustworthy reasoning trajectories. By providing binary evaluations for both the intermediate reasoning steps and the final answer, Step-KTO encourages the model to adhere to logical progressions rather than relying on superficial shortcuts. Our experiments on challenging mathematical benchmarks show that Step-KTO significantly improves both final answer accuracy and the quality of intermediate reasoning steps. For example, on the MATH-500 dataset, Step-KTO achieves a notable improvement in Pass@1 accuracy over strong baselines. These results highlight the promise of integrating stepwise process feedback into LLM training, paving the way toward more interpretable and dependable reasoning capabilities.

📄 PDF Abstract BibTeX arXiv:2501.10799

Code (0)

등록된 구현이 없습니다.

Tasks

MathMathematical Reasoning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Stepwise Think-Critique: A Unified Framework for Robust and Interpretable LLM Reasoning

2025-12-17 · Jiaqi Xu, Cuiling Lan, Xuejin Chen, Yan Lu arxiv

Human beings solve complex problems through critical thinking, where reasoning and evaluation are intertwined to converge toward correct solutions. However, most existing large language models (LLMs) treat the reasoning …

Reinforcement LearningMathematical Reasoning

Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning

2024-06-30 · Zimu Lu, Aojun Zhou, Ke Wang, Houxing Ren 외

Direct Preference Optimization (DPO) has proven effective at improving the performance of large language models (LLMs) on downstream tasks such as reasoning and alignment. In this work, we propose Step-Controlled DPO (SC…

GSM8KMathMathematical Reasoning

Stepwise Self-Consistent Mathematical Reasoning with Large Language Models

2024-02-24 · Zilong Zhao, Yao Rong, Dongyang Guo, Emek Gözlüklü 외

Using Large Language Models for complex mathematical reasoning is difficult, primarily due to the complexity of multi-step reasoning. The main challenges of this process include (1) selecting critical intermediate result…

MathMathematical Reasoning

Improving Reasoning Capabilities in Small Models through Mixture-of-Layers Distillation with Stepwise Attention on Key Information

2026-04-17 · Yao Chen, Jiawei Sheng, Wenyuan Zhang, Tingwen Liu arxiv

The significant computational demands of large language models have increased interest in distilling reasoning abilities into smaller models via Chain-of-Thought (CoT) distillation. Current CoT distillation methods mainl…

Enhancing Mathematical Reasoning in LLMs by Stepwise Correction

2024-10-16 · Zhenyu Wu, Qingkai Zeng, Zhihan Zhang, Zhaoxuan Tan 외

Best-of-N decoding methods instruct large language models (LLMs) to generate multiple solutions, score each using a scoring function, and select the highest scored as the final answer to mathematical reasoning problems. …

Mathematical Reasoning