paper-with-me

Papers Math Word Problem Solving

“Math Word Problem Solving” 태그가 달린 논문 107편 · 필터 해제

A Diversity-Enhanced Knowledge Distillation Model for Practical Math Word Problem Solving

2025-01-07 · Yi Zhang, Guangyou Zhou, Zhiwen Xie, Jinjin Ma 외

Math Word Problem (MWP) solving is a critical task in natural language processing, has garnered significant research interest in recent years. Various recent studies heavily rely on Seq2Seq models and their extensions (e…

DiversityKnowledge DistillationMathMath Word Problem Solving

Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval

2024-11-25 · Xiaocong Yang, Jiacheng Lin, Ziqi Wang, ChengXiang Zhai

Large language models (LLMs) are known to struggle with complicated reasoning tasks such as math word problems (MWPs). In this paper, we present how analogy from similarly structured questions can improve LLMs' problem-s…

MathMath Word Problem SolvingRetrieval

SBI-RAG: Enhancing Math Word Problem Solving for Students through Schema-Based Instruction and Retrieval-Augmented Generation

2024-10-17 · Prakhar Dixit, Tim Oates

Many students struggle with math word problems (MWPs), often finding it difficult to identify key information and select the appropriate mathematical operations. Schema-based instruction (SBI) is an evidence-based strate…

GSM8KLanguage ModelingLanguage ModellingLarge Language Model+5

When Not to Answer: Evaluating Prompts on GPT Models for Effective Abstention in Unanswerable Math Word Problems

2024-10-16 · Asir Saadat, Tasmia Binte Sogir, Md Taukir Azam Chowdhury, Syem Aziz

Large language models (LLMs) are increasingly relied upon to solve complex mathematical word problems. However, being susceptible to hallucination, they may generate inaccurate results when presented with unanswerable qu…

HallucinationMathMath Word Problem Solving

Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models

2024-10-10 · Wenting Tan, Dongxiao Chen, Jieting Xue, ZiHao Wang 외

Large Language Models (LLMs) exhibit impressive performance across various domains but still struggle with arithmetic reasoning tasks. Recent work shows the effectiveness of prompt design methods in enhancing reasoning c…

Arithmetic ReasoningMathMathematical ReasoningMath Word Problem Solving

OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data

2024-10-02 · Shubham Toshniwal, Wei Du, Ivan Moshkov, Branislav Kisacanin 외

Mathematical reasoning continues to be a critical challenge in large language model (LLM) development with significant interest. However, most of the cutting-edge progress in mathematical reasoning with LLMs has become \…

Arithmetic ReasoningLarge Language ModelMathMathematical Reasoning+1

Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

2024-09-18 · An Yang, Beichen Zhang, Binyuan Hui, Bofei Gao 외

In this report, we present a series of math-specific large language models: Qwen2.5-Math and Qwen2.5-Math-Instruct-1.5B/7B/72B. The core innovation of the Qwen2.5 series lies in integrating the philosophy of self-improve…

GSM8KMathMathematical ReasoningMath Word Problem Solving+1

Qwen2 Technical Report

2024-07-15 · An Yang, Baosong Yang, Binyuan Hui, Bo Zheng 외

This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models. We release a comprehensive suite of foundational and instruction-tuned language models, encompassing …

Arithmetic ReasoningGSM8KHumanEvalLanguage Modelling+4

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

2024-06-26 · Xin Lai, Zhuotao Tian, Yukang Chen, Senqiao Yang 외

Mathematical reasoning presents a significant challenge for Large Language Models (LLMs) due to the extensive and precise chain of reasoning required for accuracy. Ensuring the correctness of each reasoning step is criti…

Arithmetic ReasoningGSM8KMathMathematical Reasoning+1

DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving

2024-06-18 · Yuxuan Tong, Xiwen Zhang, Rui Wang, Ruidong Wu 외

Solving mathematical problems requires advanced reasoning abilities and presents notable challenges for large language models. Previous works usually synthesize data from proprietary models to augment existing datasets, …

Arithmetic ReasoningMathMathematical Problem-SolvingMath Word Problem Solving+1

Program Synthesis Benchmark for Visual Programming in XLogoOnline Environment

2024-06-17 · Chao Wen, Jacqueline Staub, Adish Singla

Large language and multimodal models have shown remarkable successes on various benchmarks focused on specific skills such as general-purpose programming, natural language understanding, math word problem-solving, and vi…

Logical ReasoningMathMath Word Problem SolvingNatural Language Understanding+3

AlphaMath Almost Zero: Process Supervision without Process

2024-05-06 · Guoxin Chen, Minpeng Liao, Chengxi Li, Kai Fan

Although recent advancements in large language models (LLMs) have significantly improved their performance on various tasks, they still face challenges with complex and symbolic multi-step reasoning, particularly in math…

Mathematical ReasoningMath Word Problem Solving

Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems

2024-04-23 · Qihuang Zhong, Kang Wang, Ziyang Xu, Juhua Liu 외

Chain-of-Thought (CoT) prompting has enhanced the performance of Large Language Models (LLMs) across various reasoning tasks. However, CoT still falls short in dealing with complex math word problems, as it usually suffe…

Arithmetic ReasoningGSM8KMathMath Word Problem Solving

Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing

2024-04-18 · Ye Tian, Baolin Peng, Linfeng Song, Lifeng Jin 외

Despite the impressive capabilities of Large Language Models (LLMs) on various tasks, they still struggle with scenarios that involves complex reasoning and planning. Recent work proposed advanced prompting techniques an…

Arithmetic ReasoningGSM8KMathMathematical Reasoning+2

MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems

2024-04-06 · Bin Lei, Yi Zhang, Shan Zuo, Ali Payani 외

Recent advancements in large language models, such as GPT-4, have demonstrated remarkable capabilities in processing standard queries. Despite these advancements, their performance substantially declines in \textbf{advan…

Logical ReasoningMathMath Word Problem Solving

Data Augmentation with In-Context Learning and Comparative Evaluation in Math Word Problem Solving

2024-04-05 · Gulsum Yigit, Mehmet Fatih Amasyali

Math Word Problem (MWP) solving presents a challenging task in Natural Language Processing (NLP). This study aims to provide MWP solvers with a more diverse training set, ultimately improving their ability to solve vario…

Data AugmentationIn-Context LearningLanguage ModelingLanguage Modelling+2

Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM

2024-03-12 · Sainbayar Sukhbaatar, Olga Golovneva, Vasu Sharma, Hu Xu 외

We investigate efficient methods for training Large Language Models (LLMs) to possess capabilities in multiple specialized domains, such as coding, math reasoning and world knowledge. Our method, named Branch-Train-MiX (…

Arithmetic ReasoningCode GenerationCommon Sense ReasoningMath+5

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

2024-03-08 · Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell 외

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions …

1 Image, 2*2 StitchingCode GenerationFS-MEVQAImage Retrieval+8

Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning

2024-03-04 · Yiming Huang, Xiao Liu, Yeyun Gong, Zhibin Gou 외

Large language models (LLMs) have shown great potential in complex reasoning tasks, yet their performance is often hampered by the scarcity of high-quality and reasoning-focused training datasets. Addressing this challen…

GSM8KMathMathematical ReasoningMath Word Problem Solving

GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers

2024-02-29 · Qintong Li, Leyang Cui, Xueliang Zhao, Lingpeng Kong 외

Large language models (LLMs) have achieved impressive performance across various mathematical reasoning benchmarks. However, there are increasing debates regarding whether these models truly understand and apply mathemat…

GSM8KMathMathematical ReasoningMath Word Problem Solving
1–20 / 107 다음 →