paper-with-me

Papers

How Numerical Precision Affects Mathematical Reasoning Capabilities of LLMs

2024-10-17 · Guhao Feng, Kai Yang, Yuntian Gu, Xinyue Ai, Shengjie Luo, Jiacheng Sun, Di He, Zhenguo Li, LiWei Wang

Despite the remarkable success of Transformer-based Large Language Models (LLMs) across various domains, understanding and enhancing their mathematical capabilities remains a significant challenge. In this paper, we conduct a rigorous theoretical analysis of LLMs' mathematical abilities, with a specific focus on their arithmetic performances. We identify numerical precision as a key factor that influences their effectiveness in mathematical tasks. Our results show that Transformers operating with low numerical precision fail to address arithmetic tasks, such as iterated addition and integer multiplication, unless the model size grows super-polynomially with respect to the input length. In contrast, Transformers with standard numerical precision can efficiently handle these tasks with significantly smaller model sizes. We further support our theoretical findings through empirical experiments that explore the impact of varying numerical precision on arithmetic tasks, providing valuable insights for improving the mathematical reasoning capabilities of LLMs.

📄 PDF Abstract BibTeX arXiv:2410.13857

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical Reasoning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning

2025-01-06 · Zhen Li, Yupeng Su, Runming Yang, Zhongwei Xie 외

Large language models have achieved significant advancements in complex mathematical reasoning benchmarks, such as MATH. However, their substantial computational requirements present challenges for practical deployment. …

MathMathematical ReasoningQuantization

MathMist: A Parallel Multilingual Benchmark Dataset for Mathematical Problem Solving and Reasoning

2025-10-16 · Mahbub E Sobhani, Md. Faiyaz Abdullah Sayeedi, Tasnim Mohiuddin, Md Mofijul Islam 외 arxiv

Mathematical reasoning remains one of the most challenging domains for large language models (LLMs), requiring not only linguistic understanding but also structured logical deduction and numerical precision. While recent…

Mathematical Reasoning

Scaling Generative Verifiers For Natural Language Mathematical Proof Verification And Selection

2025-11-17 · Sadegh Mahdavi, Branislav Kisacanin, Shubham Toshniwal, Wei Du 외 arxiv

Large language models have achieved remarkable success on final-answer mathematical problems, largely due to the ease of applying reinforcement learning with verifiable rewards. However, the reasoning underlying these so…

Reinforcement Learning

LexPam: Legal Procedure Awareness-Guided Mathematical Reasoning

2025-04-03 · Kepu Zhang, Guofu Xie, Weijie Yu, Mingyue Xu 외

The legal mathematical reasoning ability of LLMs is crucial when applying them to real-world scenarios, as it directly affects the credibility of the LLM. While existing legal LLMs can perform general judicial question a…

Mathematical ReasoningQuestion Answering

A Survey on Mathematical Reasoning and Optimization with Large Language Models

2025-03-22 · Ali Forootani

Mathematical reasoning and optimization are fundamental to artificial intelligence and computational problem-solving. Recent advancements in Large Language Models (LLMs) have significantly improved AI-driven mathematical…

Automated Theorem ProvingHeuristic SearchMathematical Problem-SolvingMathematical Reasoning+2