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/hkust-nlp/b-star

공식 코드

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners

https://github.com/hkust-nlp/dart-math

공식 코드

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

https://github.com/hkust-nlp/guimid

공식 코드

Breaking the Data Barrier -- Building GUI Agents Through Task Generalization

https://github.com/hkust-nlp/llm-compression-intelligence

공식 코드

Compression Represents Intelligence Linearly

https://github.com/hlr/blind

공식 코드

Reasoning over Uncertain Text by Generative Large Language Models

https://github.com/hlzhang109/causal-eval

공식 코드

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning

https://github.com/homzer/MCC-KD

공식 코드

MCC-KD: Multi-CoT Consistent Knowledge Distillation

https://github.com/homzer/q-rm

공식 코드

Discriminative Policy Optimization for Token-Level Reward Models

https://github.com/hqhqaq/hint-grpo

공식 코드

Boosting MLLM Reasoning with Text-Debiased Hint-GRPO

https://github.com/hzq950419/math-llava

공식 코드

Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models

https://github.com/idrori/mathq

공식 코드

A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level

https://github.com/iiis-ai/cumulative-reasoning

공식 코드

Cumulative Reasoning with Large Language Models

https://github.com/iiis-ai/iterativequestioncomposing

공식 코드

Augmenting Math Word Problems via Iterative Question Composing

https://github.com/iiis-ai/templatemath

공식 코드

Training and Evaluating Language Models with Template-based Data Generation

https://github.com/ikb-a/curious-case

공식 코드

Library Learning Doesn't: The Curious Case of the Single-Use "Library"

https://github.com/imoneoi/openchat

공식 코드

OpenChat: Advancing Open-source Language Models with Mixed-Quality Data

https://github.com/internlm/internlm-math

공식 코드

LEAN-GitHub: Compiling GitHub LEAN repositories for a versatile LEAN prover

https://github.com/internlm/internlm-xcomposer

공식 코드

InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model

https://github.com/internlm/oreal

공식 코드

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

https://github.com/ist-daslab/mathador-lm

공식 코드

Mathador-LM: A Dynamic Benchmark for Mathematical Reasoning on Large Language Models

https://github.com/jacksun200312/ecp

공식 코드

Enumerate-Conjecture-Prove: Formally Solving Answer-Construction Problems in Math Competitions

https://github.com/jason8kang/tell

공식 코드

Template-Driven LLM-Paraphrased Framework for Tabular Math Word Problem Generation

https://github.com/jcguo123/temporal-consistency

공식 코드

Temporal Consistency for LLM Reasoning Process Error Identification

https://github.com/jcruan519/vlrmbench

공식 코드

VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models

https://github.com/jiahao004/deeptheorem

공식 코드

DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning

https://github.com/jincan333/MAS-TTS

공식 코드

Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning

https://github.com/jinyangwu/HiARICL

공식 코드

Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS

https://github.com/jjzha/fs1

공식 코드

Scaling Reasoning can Improve Factuality in Large Language Models

https://github.com/jlrussin/interpret-math-transformer

공식 코드

Compositional Processing Emerges in Neural Networks Solving Math Problems

https://github.com/jnanliu/situatedthinker

공식 코드

SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking

https://github.com/joshuaongg21/comat

공식 코드

CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning

https://github.com/joykirat18/syrelm

공식 코드

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

https://github.com/juletx/self-translate

공식 코드

Do Multilingual Language Models Think Better in English?

https://github.com/junyiye/creativemath

공식 코드

Assessing the Creativity of LLMs in Proposing Novel Solutions to Mathematical Problems

https://github.com/juzhengz/lori

공식 코드

LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation

https://github.com/jwhj/oreo

공식 코드

Offline Reinforcement Learning for LLM Multi-Step Reasoning

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