Papers with Code 아카이브
Math Word Problem Solving
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 13
- 보존된 평가 기록
- 245
A math word problem is a mathematical exercise (such as in a textbook, worksheet, or exam) where significant background information on the problem is presented in ordinary language rather than in mathematical notation. As most word problems involve a narrative of some sort, they are sometimes referred to as story problems and may vary in the amount of technical language used.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval
SBI-RAG: Enhancing Math Word Problem Solving for Students through Schema-Based Instruction and Retrieval-Augmented Generation
When Not to Answer: Evaluating Prompts on GPT Models for Effective Abstention in Unanswerable Math Word Problems
Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models
OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data
Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
Qwen2 Technical Report
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving
Program Synthesis Benchmark for Visual Programming in XLogoOnline Environment
AlphaMath Almost Zero: Process Supervision without Process
Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems
Data Augmentation with In-Context Learning and Comparative Evaluation in Math Word Problem Solving
Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning
GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers
An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Augmenting Math Word Problems via Iterative Question Composing
Mixtral of Experts
Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks
Gemini: A Family of Highly Capable Multimodal Models
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
Frugal LMs Trained to Invoke Symbolic Solvers Achieve Parameter-Efficient Arithmetic Reasoning
FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains
VerityMath: Advancing Mathematical Reasoning by Self-Verification Through Unit Consistency
ATHENA: Mathematical Reasoning with Thought Expansion
An Expression Tree Decoding Strategy for Mathematical Equation Generation
Mistral 7B
MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning
MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.