Papers with Code 아카이브

Mathematical Reasoning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

7

평가표

11

보존된 평가 기록

41

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/wongzhenhao/GameRL

공식 코드

LogicPuzzleRL: Cultivating Robust Mathematical Reasoning in LLMs via Reinforcement Learning

https://github.com/wufeiwuwoshihua/lexicaldiver

공식 코드

Are LLMs Reliable Translators of Logical Reasoning Across Lexically Diversified Contexts?

https://github.com/wuhy68/parameter-efficient-moe

공식 코드

Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks

https://github.com/wumingqi/LLM-Math-Evaluation

공식 코드

Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination

https://github.com/wwzhuang01/math-puma

공식 코드

Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning

https://github.com/wzy6642/I3C-Select

공식 코드

Instructing Large Language Models to Identify and Ignore Irrelevant Conditions

https://github.com/xiaolizh1/epicprm

공식 코드

An Efficient and Precise Training Data Construction Framework for Process-supervised Reward Model in Mathematical Reasoning

https://github.com/xiaolizh1/ktae

공식 코드

KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning

https://github.com/xinxu-ustc/coleg-math

공식 코드

Can LLMs Solve longer Math Word Problems Better?

https://github.com/xinyan-cxy/mint-cot

공식 코드

MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning

https://github.com/xiwenc1/dra-grpo

공식 코드

DRA-GRPO: Exploring Diversity-Aware Reward Adjustment for R1-Zero-Like Training of Large Language Models

https://github.com/xiye17/explselection

공식 코드

Explanation Selection Using Unlabeled Data for Chain-of-Thought Prompting

https://github.com/xu1998hz/llm_self_bias

공식 코드

Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement

https://github.com/xuzhao0/model-selection-reasoning

공식 코드

Automatic Model Selection with Large Language Models for Reasoning

https://github.com/xyfrieder/science-ghosts

공식 코드

Mathematical Capabilities of ChatGPT

https://github.com/xyliu-cs/rise

공식 코드

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards

https://github.com/yale-nlp/knowledgemath

공식 코드

FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains

https://github.com/yangjie-cv/wethink

공식 코드

WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning

https://github.com/yangling0818/buffer-of-thought-llm

공식 코드

Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

https://github.com/yangling0818/supercorrect-llm

공식 코드

SuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights

https://github.com/yangyi-chen/solo

공식 코드

SOLO: A Single Transformer for Scalable Vision-Language Modeling

https://github.com/yangzhch6/ReSocratic

공식 코드

OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling

https://github.com/yangzhch6/alignedcot

공식 코드

AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations

https://github.com/yangzhch6/intermwp

공식 코드

LogicSolver: Towards Interpretable Math Word Problem Solving with Logical Prompt-enhanced Learning

https://github.com/yc1999/LLM2

공식 코드

LLM2: Let Large Language Models Harness System 2 Reasoning

https://github.com/ycpnotfound/geogen

공식 코드

Enhancing the Geometric Problem-Solving Ability of Multimodal LLMs via Symbolic-Neural Integration

https://github.com/yetianjhu/alphallm

공식 코드

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

https://github.com/yifanzhang-pro/automathtext

공식 코드

Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts

https://github.com/yijia-xiao/logicvista

공식 코드

LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts

https://github.com/yiranwu0/mathchat

공식 코드

MathChat: Converse to Tackle Challenging Math Problems with LLM Agents

https://github.com/yiyunya/RODA

공식 코드

Reverse Operation based Data Augmentation for Solving Math Word Problems

https://github.com/yoshikitakashima/scheherazade-code-data

공식 코드

Scheherazade: Evaluating Chain-of-Thought Math Reasoning in LLMs with Chain-of-Problems

https://github.com/ypwang61/one-shot-rlvr

공식 코드

Reinforcement Learning for Reasoning in Large Language Models with One Training Example

https://github.com/ytyz1307zzh/RefAug

공식 코드

Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning

https://github.com/yu-fangxu/for

공식 코드

Flow of Reasoning:Training LLMs for Divergent Problem Solving with Minimal Examples

https://github.com/yue-llm-pit/scop

공식 코드

Paraphrase and Solve: Exploring and Exploiting the Impact of Surface Form on Mathematical Reasoning in Large Language Models

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.