paper-with-me

Papers

NaturalProver: Grounded Mathematical Proof Generation with Language Models

2022-05-25 · Sean Welleck, Jiacheng Liu, Ximing Lu, Hannaneh Hajishirzi, Yejin Choi

Theorem proving in natural mathematical language - the mixture of symbolic and natural language used by humans - plays a central role in mathematical advances and education, and tests aspects of reasoning that are core to intelligence. Yet it has remained underexplored with modern generative models. We study large-scale language models on two new generation tasks: suggesting the next step in a mathematical proof, and full proof generation. We develop NaturalProver, a language model that generates proofs by conditioning on background references (e.g. theorems and definitions that are either retrieved or human-provided), and optionally enforces their presence with constrained decoding. On theorems from the NaturalProofs benchmark, NaturalProver improves the quality of next-step suggestions and generated proofs over fine-tuned GPT-3, according to human evaluations from university-level mathematics students. NaturalProver is capable of proving some theorems that require short (2-6 step) proofs, and providing next-step suggestions that are rated as correct and useful over 40% of the time, which is to our knowledge the first demonstration of these capabilities using neural language models.

📄 PDF Abstract BibTeX arXiv:2205.12910

Code (1)

wellecks/naturalprover 공식 구현

Tasks

Automated Theorem ProvingLanguage ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Adam 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…

Similar Papers 제목 키워드 기반

Linear Reasoning vs. Proof by Cases: Obstacles for Large Language Models in FOL Problem Solving

2026-02-24 · Yuliang Ji, Fuchen Shen, Jian Wu, Qiujie Xie 외 arxiv

To comprehensively evaluate the mathematical reasoning capabilities of Large Language Models (LLMs), researchers have introduced abundant mathematical reasoning datasets. However, most existing datasets primarily focus o…

Mathematical Reasoning

Re$^2$Math: Benchmarking Theorem Retrieval in Research-Level Mathematics

2026-05-09 · Zicheng Lyu, Wenjie Yang, Shengzhong Zhang, Zengfeng Huang arxiv

Large language models are increasingly capable at closed-world mathematical reasoning, but research assistance also requires source-grounded use of the literature. When a proof reaches a non-trivial step, a useful assist…

Mathematical Reasoning

NaturalProofs: Mathematical Theorem Proving in Natural Language

2021-03-24 · Sean Welleck, Jiacheng Liu, Ronan Le Bras, Hannaneh Hajishirzi 외

Understanding and creating mathematics using natural mathematical language - the mixture of symbolic and natural language used by humans - is a challenging and important problem for driving progress in machine learning. …

Automated Theorem ProvingDomain GeneralizationInformation RetrievalRetrieval+1

LemmaHead: RAG Assisted Proof Generation Using Large Language Models

2025-01-27 · Tianbo Yang, Mingqi Yang, Hongyi Zhao, Tianshuo Yang

Developing the logic necessary to solve mathematical problems or write mathematical proofs is one of the more difficult objectives for large language models (LLMS). Currently, the most popular methods in literature consi…

Automated Theorem ProvingMathematical ProofsMathematical ReasoningRAG+1

Andy: A Mathematical Agent for Rigorous Proof and Autonomous Research

2026-08-15 · Zi'an Wang arxiv

Andy is an autonomous mathematical research agent that turns a mathematical problem into a traceable proof. It solves or verifies a submitted problem, formulates a literature-grounded new problem through a research-value…