7 papers
Co-Authoring with AI: How I Wrote a Physics Paper About AI, Using AI
Yi Zhou
The rapid integration of Large Language Models (LLMs) into scientific writing fundamentally challenges traditional definitions of authorship, responsibility, and scientific integri…
From Paper to Program: Specification-Guided Implementation of Quantum Many-Body Algorithms with Large Language Model
Yi Zhou
Turning scientific papers into reliable code requires making implicit computational knowledge explicit. We introduce and evaluate a human-supervised workflow in which large languag…
Adaptive Confidence Gating in Multi-Agent Collaboration for Efficient and Optimized Code Generation
Haoji Zhang, Yuzhe Li, Zhenqiang Liu +3
While Large Language Models (LLMs) have catalyzed breakthroughs in automated code generation, Small Language Models (SLMs) often encounter reasoning bottlenecks and failure loops w…
KELPS: A Framework for Verified Multi-Language Autoformalization via Semantic-Syntactic Alignment
Jiyao Zhang, Chengli Zhong, Hui Xu +2
Modern large language models (LLMs) show promising progress in formalizing informal mathematics into machine-verifiable theorems. However, these methods still face bottlenecks due…
Brain-Inspired Two-Stage Approach: Enhancing Mathematical Reasoning by Imitating Human Thought Processes
Yezeng Chen, Zui Chen, Yi Zhou
Although large language models demonstrate emergent abilities in solving math word problems, there is a challenging task in complex multi-step mathematical reasoning tasks. To impr…
An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning
Zui Chen, Yezeng Chen, Jiaqi Han +3
Large language models (LLMs) are displaying emergent abilities for math reasoning tasks,and there is a growing attention on enhancing the ability of open-source LLMs through superv…
Conic10K: A Challenging Math Problem Understanding and Reasoning Dataset
Haoyi Wu, Wenyang Hui, Yezeng Chen +3
Mathematical understanding and reasoning are crucial tasks for assessing the capabilities of artificial intelligence (AI). However, existing benchmarks either require just a few st…