Papers with Code 아카이브

GSM8K

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

2

보존된 평가 기록

3

코드

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

https://github.com/mathllm/mathcoder

공식 코드

MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning

https://github.com/mcgill-nlp/vineppo

공식 코드

VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment

https://github.com/meta-math/MetaMath

공식 코드

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

https://github.com/meta-prompting/meta-prompting

공식 코드

Meta Prompting for AI Systems

https://github.com/microsoft/LLMLingua

공식 코드

LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models

https://github.com/microsoft/MathOctopus

공식 코드

Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations

https://github.com/microsoft/lema

공식 코드

Learning From Mistakes Makes LLM Better Reasoner

https://github.com/microsoft/tracecodegen

공식 코드

Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions

https://github.com/microsoft/unilm/tree/master/mathscale

공식 코드

MathScale: Scaling Instruction Tuning for Mathematical Reasoning

https://github.com/mikegu721/agentgroupchat-v2

공식 코드

AgentGroupChat-V2: Divide-and-Conquer Is What LLM-Based Multi-Agent System Need

https://github.com/minwukim/GSM-Ranges

공식 코드

Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges

https://github.com/ml-gsai/smdm

공식 코드

Scaling up Masked Diffusion Models on Text

https://github.com/mlbio-epfl/joint-inference

공식 코드

Large (Vision) Language Models are Unsupervised In-Context Learners

https://github.com/mohammadrezabanaei/lora-xs

공식 코드

LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters

https://github.com/mukhal/grace

공식 코드

GRACE: Discriminator-Guided Chain-of-Thought Reasoning

https://github.com/ningmiao/selfcheck

공식 코드

SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning

https://github.com/ofa-sys/gsm8k-screl

공식 코드

Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

https://github.com/open-compass/mathbench

공식 코드

MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark

https://github.com/openai/grade-school-math

공식 코드

Training Verifiers to Solve Math Word Problems

https://github.com/optimalscale/lmflow

공식 코드

LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning

https://github.com/outsider565/lora-ga

공식 코드

LoRA-GA: Low-Rank Adaptation with Gradient Approximation

https://github.com/pdx97/sbi-rag_neurips2024

공식 코드

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

https://github.com/pphuc25/distil-cd

공식 코드

Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation

https://github.com/princeton-nlp/lm-science-tutor

공식 코드

Language Models as Science Tutors

https://github.com/prompteus/calc-x

공식 코드

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

https://github.com/psunlpgroup/greater

공식 코드

GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers

https://github.com/qbetterk/VarBench

공식 코드

VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation

https://github.com/qiancheng0/open-smartagent

공식 코드

SMART: Self-Aware Agent for Tool Overuse Mitigation

https://github.com/qinyiwei/dive

공식 코드

DIVE: Diversified Iterative Self-Improvement

https://github.com/qqq-yi/dac

공식 코드

DAC: A Dynamic Attention-aware Approach for Task-Agnostic Prompt Compression

https://github.com/qtli/gsm-plus

공식 코드

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

https://github.com/qwenlm/processbench

공식 코드

ProcessBench: Identifying Process Errors in Mathematical Reasoning

https://github.com/qwenlm/qwen2

공식 코드

Qwen2 Technical Report

https://github.com/rajasekharmekala/query-rephrasing-subtask-cot

공식 코드

EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learning

https://github.com/rioyokotalab/swallow-code-math

공식 코드

Rewriting Pre-Training Data Boosts LLM Performance in Math and Code

https://github.com/salesforceairesearch/latro

공식 코드

Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding

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