paper-with-me

Papers

Neural Arithmetic Expression Calculator

2018-09-23 · Kaiyu Chen, Yihan Dong, Xipeng Qiu, Zitian Chen

This paper presents a pure neural solver for arithmetic expression calculation (AEC) problem. Previous work utilizes the powerful capabilities of deep neural networks and attempts to build an end-to-end model to solve this problem. However, most of these methods can only deal with the additive operations. It is still a challenging problem to solve the complex expression calculation problem, which includes the adding, subtracting, multiplying, dividing and bracketing operations. In this work, we regard the arithmetic expression calculation as a hierarchical reinforcement learning problem. An arithmetic operation is decomposed into a series of sub-tasks, and each sub-task is dealt with by a skill module. The skill module could be a basic module performing elementary operations, or interactive module performing complex operations by invoking other skill models. With curriculum learning, our model can deal with a complex arithmetic expression calculation with the deep hierarchical structure of skill models. Experiments show that our model significantly outperforms the previous models for arithmetic expression calculation.

📄 PDF Abstract BibTeX arXiv:1809.08590

Code (0)

등록된 구현이 없습니다.

Tasks

Hierarchical Reinforcement LearningReinforcement Learning

Similar Papers 제목 키워드 기반

IGC: Integrating a Gated Calculator into an LLM to Solve Arithmetic Tasks Reliably and Efficiently

2025-01-01 · Florian Dietz, Dietrich Klakow

Solving arithmetic tasks is a simple and fundamental skill, yet modern Large Language Models (LLMs) have great difficulty with them. We introduce the Integrated Gated Calculator (IGC), a module that enables LLMs to perfo…

GPU

Frugal LMs Trained to Invoke Symbolic Solvers Achieve Parameter-Efficient Arithmetic Reasoning

2023-12-09 · Subhabrata Dutta, Joykirat Singh, Ishan Pandey, Sunny Manchanda 외

Large Language Models (LLM) exhibit zero-shot mathematical reasoning capacity as a behavior emergent with scale, commonly manifesting as chain-of-thoughts (CoT) reasoning. However, multiple empirical findings suggest tha…

Arithmetic ReasoningMathematical ReasoningMath Word Problem Solving

Towards a Deterministic Math Solver for Clinical Language Models

2026-09-09 · Felipe Ocampo Osorio, Sebastián Andrés Cajas Ordoñez, Maximin Lange, Rafi Al Attrach 외 hf

Large language models are unreliable at arithmetic, which is a problem for clinical calculators where a single numerical error changes the recommendation. The standard response is to hardcode each calculator as a validat…

GPT Can Solve Mathematical Problems Without a Calculator

2023-09-06 · Zhen Yang, Ming Ding, Qingsong Lv, Zhihuan Jiang 외

Previous studies have typically assumed that large language models are unable to accurately perform arithmetic operations, particularly multiplication of >8 digits, and operations involving decimals and fractions, withou…

Language ModelingLanguage ModellingMath

Calc-X and Calcformers: Empowering Arithmetical Chain-of-Thought through Interaction with Symbolic Systems

2023-05-24 · Marek Kadlčík, Michal Štefánik, Ondřej Sotolář, Vlastimil Martinek

Despite outstanding performance in many tasks, language models are notoriously inclined to make factual errors in tasks requiring arithmetic computation. We address this deficiency by creating Calc-X, a collection of dat…

Arithmetic ReasoningGSM8KLanguage ModelingLanguage Modelling