paper-with-me

홈 › Papers

Limits of an AI program for solving college math problems

2022-08-14 · Ernest Davis

Drori et al. (2022) report that "A neural network solves, explains, and generates university math problems by program synthesis and few-shot learning at human level ... [It] automatically answers 81\% of university-level mathematics problems." The system they describe is indeed impressive; however, the above description is very much overstated. The work of solving the problems is done, not by a neural network, but by the symbolic algebra package Sympy. Problems of various formats are excluded from consideration. The so-called "explanations" are just rewordings of lines of code. Answers are marked as correct that are not in the form specified in the problem. Most seriously, it seems that in many cases the system uses the correct answer given in the test corpus to guide its path to solving the problem.

📄 PDF Abstract BibTeX arXiv:2208.06906

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot LearningMathProgram Synthesis

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains

2023-11-16 · Yilun Zhao, Hongjun Liu, Yitao Long, Rui Zhang 외

We introduce FinanceMath, a novel benchmark designed to evaluate LLMs' capabilities in solving knowledge-intensive math reasoning problems. Compared to prior works, this study features three core advancements. First, Fin…

MathMath Word Problem SolvingRetrieval

ChatGPT-4 with Code Interpreter can be used to solve introductory college-level vector calculus and electromagnetism problems

2023-09-16 · Tanuj Kumar, Mikhail A. Kats

We evaluated ChatGPT 3.5, 4, and 4 with Code Interpreter on a set of college-level engineering-math and electromagnetism problems, such as those often given to sophomore electrical engineering majors. We selected a set o…

Electrical EngineeringMath

MathScale: Scaling Instruction Tuning for Mathematical Reasoning

2024-03-05 · Zhengyang Tang, Xingxing Zhang, Benyou Wan, Furu Wei

Large language models (LLMs) have demonstrated remarkable capabilities in problem-solving. However, their proficiency in solving mathematical problems remains inadequate. We propose MathScale, a simple and scalable metho…

GSM8KMathMathematical Reasoning

VerityMath: Advancing Mathematical Reasoning by Self-Verification Through Unit Consistency

2023-11-13 · Vernon Toh Yan Han, Ratish Puduppully, Nancy F. Chen

Large Language Models (LLMs), combined with program-based solving techniques, are increasingly demonstrating proficiency in mathematical reasoning. For example, closed-source models such as OpenAI GPT-4 and Claude show e…

MathMathematical ReasoningMath Word Problem Solving

Solving Quantitative Reasoning Problems with Language Models

2022-06-29 · Aitor Lewkowycz, Anders Andreassen, David Dohan, Ethan Dyer 외

Language models have achieved remarkable performance on a wide range of tasks that require natural language understanding. Nevertheless, state-of-the-art models have generally struggled with tasks that require quantitati…

Arithmetic ReasoningLanguage ModelingLanguage ModellingLarge Language Model+3