홈 › Papers

MathChat: Converse to Tackle Challenging Math Problems with LLM Agents

2023-06-02 · Yiran Wu, Feiran Jia, Shaokun Zhang, Hangyu Li, Erkang Zhu, Yue Wang, Yin Tat Lee, Richard Peng, Qingyun Wu, Chi Wang

Employing Large Language Models (LLMs) to address mathematical problems is an intriguing research endeavor, considering the abundance of math problems expressed in natural language across numerous science and engineering fields. LLMs, with their generalized ability, are used as a foundation model to build AI agents for different tasks. In this paper, we study the effectiveness of utilizing LLM agents to solve math problems through conversations. We propose MathChat, a conversational problem-solving framework designed for math problems. MathChat consists of an LLM agent and a user proxy agent which is responsible for tool execution and additional guidance. This synergy facilitates a collaborative problem-solving process, where the agents engage in a dialogue to solve the problems. We perform evaluation on difficult high school competition problems from the MATH dataset. Utilizing Python, we show that MathChat can further improve previous tool-using prompting methods by 6%.

📄 PDF Abstract BibTeX arXiv:2306.01337

Code (2)

yiranwu0/mathchat 공식 구현

qingyun-wu/autogen-eval pytorch

Tasks

Elementary MathematicsMathMath Word Problem Solving

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Residual Connection 설명 없음

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Position-Wise Feed-Forward Layer 설명 없음

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions

2024-05-29 · Zhenwen Liang, Dian Yu, Wenhao Yu, Wenlin Yao 외

Large language models (LLMs) have demonstrated impressive capabilities in mathematical problem solving, particularly in single turn question answering formats. However, real world scenarios often involve mathematical que…

Benchmarking Dialogue Understanding Instruction Following Math+4

SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models

2024-08-28 · Dian Yu, Baolin Peng, Ye Tian, Linfeng Song 외

There is a growing trend of teaching large language models (LLMs) to solve mathematical problems through coding. Existing studies primarily focus on prompting powerful, closed-source models to generate seed training data…

Data Augmentation GSM8K Math Mathematical Reasoning

Swarm Intelligence: Past, Present and Future

2018-04-21 · Xin-She Yang, Suash Deb, Yuxin Zhao, Simon Fong 외

Many optimization problems in science and engineering are challenging to solve, and the current trend is to use swarm intelligence (SI) and SI-based algorithms to tackle such challenging problems. Some significant develo…

Testing Changes in Communities for the Stochastic Block Model

2018-11-29 · Aditya Gangrade, Praveen Venkatesh, Bobak Nazer, Venkatesh Saligrama

We propose and analyze the problems of \textit{community goodness-of-fit and two-sample testing} for stochastic block models (SBM), where changes arise due to modification in community memberships of nodes. Motivated by …

Stochastic Block Model Two-sample testing

Efficient Near-Optimal Testing of Community Changes in Balanced Stochastic Block Models

2019-12-01 · NeurIPS 2019 12 · Aditya Gangrade, Praveen Venkatesh, Bobak Nazer, Venkatesh Saligrama

Two-sample testing