paper-with-me

Papers

Controllable Mathematical Reasoning via Self-Optimizing Thought Vectors

2025-10-25 · Xuying LI arxiv

We present a novel approach for controllable mathematical reasoning that leverages self-optimizing thought vectors with entropy minimization. Our method introduces learnable thought vectors that dynamically modulate the internal reasoning process of large language models. Using Gemma-2-9B on GSM8K, we achieve 90.1% accuracy with a controllability score of 0.42, demonstrating that entropy-based rewards effectively guide focused reasoning patterns without requiring external reward annotations. Our analysis reveals distinct thought vector clusters and consistent low-entropy distributions across control conditions, validating our framework for controllable AI reasoning.

📄 PDF Abstract BibTeX arXiv:2510.22132

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical Reasoning

Results from the Paper

RankTaskDatasetModelMetrics
#23 GSM8K GSM8K Controllable Mathematical Reasoning via Accuracy: 90.1

Similar Papers 제목 키워드 기반

Inference-Time Rethinking with Latent Thought Vectors for Math Reasoning

2026-02-06 · Deqian Kong, Minglu Zhao, Aoyang Qin, Bo Pang 외 arxiv

Standard chain-of-thought reasoning generates a solution in a single forward pass, committing irrevocably to each token and lacking a mechanism to recover from early errors. We introduce Inference-Time Rethinking, a gene…

Mathematical Reasoning

Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback

2025-01-18 · Yen-Ting Lin, Di Jin, Tengyu Xu, Tianhao Wu 외

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 …

MathMathematical Reasoning

Olapa-MCoT: Enhancing the Chinese Mathematical Reasoning Capability of LLMs

2023-12-29 · Shaojie Zhu, Zhaobin Wang, Chengxiang Zhuo, Hui Lu 외

CoT (Chain-of-Thought) is a way to solve reasoning problems for LLMs . Recently, many researches appear for improving the CoT capability of LLMs. In this work, we also proposed Olapa-MCoT, which is a LLMs based on llama2…

Mathematical Reasoning

Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs

2025-10-17 · Guiyao Tie, Zenghui Yuan, Zeli Zhao, Chaoran Hu 외 arxiv

Self-correction of large language models (LLMs) emerges as a critical component for enhancing their reasoning performance. Although various self-correction methods have been proposed, a comprehensive evaluation of these …

Mathematical ReasoningCode Generation

ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates

2025-02-10 · Ling Yang, Zhaochen Yu, Bin Cui, Mengdi Wang

We present that hierarchical LLM reasoning via scaling thought templates can effectively optimize the reasoning search space and outperform the mathematical reasoning capabilities of powerful LLMs like OpenAI o1-preview …

Hierarchical Reinforcement LearningLanguage ModelingMathMathematical Reasoning