paper-with-me

Papers

Mathematical Reasoning via Self-supervised Skip-tree Training

2020-06-08 · ICLR 2021 1 · Markus N. Rabe, Dennis Lee, Kshitij Bansal, Christian Szegedy

We examine whether self-supervised language modeling applied to mathematical formulas enables logical reasoning. We suggest several logical reasoning tasks that can be used to evaluate language models trained on formal mathematical statements, such as type inference, suggesting missing assumptions and completing equalities. To train language models for formal mathematics, we propose a novel skip-tree task. We find that models trained on the skip-tree task show surprisingly strong mathematical reasoning abilities, and outperform models trained on standard skip-sequence tasks. We also analyze the models' ability to formulate new conjectures by measuring how often the predictions are provable and useful in other proofs.

📄 PDF Abstract BibTeX arXiv:2006.04757

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLogical ReasoningMathematical Reasoning

Similar Papers 제목 키워드 기반

MC-NEST -- Enhancing Mathematical Reasoning in Large Language Models with a Monte Carlo Nash Equilibrium Self-Refine Tree

2024-11-23 · Gollam Rabby, Farhana Keya, Parvez Zamil, Sören Auer

Mathematical reasoning has proven to be a critical yet challenging task for large language models (LLMs), as they often struggle with complex multi-step problems. To address these limitations, we introduce the Monte Carl…

Decision MakingMathematical Reasoning

Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B

2024-06-11 · Di Zhang, Xiaoshui Huang, Dongzhan Zhou, Yuqiang Li 외

This paper introduces the MCT Self-Refine (MCTSr) algorithm, an innovative integration of Large Language Models (LLMs) with Monte Carlo Tree Search (MCTS), designed to enhance performance in complex mathematical reasonin…

Decision MakingGSM8KMathMathematical Reasoning

VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism

2025-06-10 · Congzhi Zhang, Jiawei Peng, Zhenglin Wang, Yilong Lai 외

Large Vision-Language Models (LVLMs) have shown exceptional performance in multimodal tasks, but their effectiveness in complex visual reasoning is still constrained, especially when employing Chain-of-Thought prompting …

Mathematical ReasoningVisual Reasoning

Domain-Specialized Tree of Thought through Plug-and-Play Predictors

2026-03-14 · Xuanqi Gao, Haoyu Wang, Jun Sun, Shiqing Ma 외 arxiv

While Large Language Models (LLMs) have advanced complex reasoning, prominent methods like the Tree of Thoughts (ToT) framework face a critical trade-off between exploration depth and computational efficiency. Existing T…

Computational EfficiencyMathematical ReasoningLogical Reasoning

Masked-and-Reordered Self-Supervision for Reinforcement Learning from Verifiable Rewards

2025-11-21 · Zhen Wang, Zhifeng Gao, Guolin Ke arxiv

Test-time scaling has been shown to substantially improve large language models' (LLMs) mathematical reasoning. However, for a large portion of mathematical corpora, especially theorem proving, RLVR's scalability is limi…

Reinforcement LearningMathematical Reasoning